Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of personal engagement and emotional responses to reading experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "I" before verbs like read, recommend, enjoy, or like

    np_acts-logits-general · gemini-2.0-flash

    I enjoyed reading or recommending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.74
    اعمال
    -0.57
     songwriter
    -0.53
     sculptor
    -0.52
     Visitors
    -0.51
     beobachtet
    -0.49
    Visitors
    -0.49
    rifice
    -0.49
     photographers
    -0.49
    ArrowToggle
    -0.48
    POSITIVE LOGITS
     enjoyment
    0.76
     spoiler
    0.75
     reread
    0.74
     recommending
    0.74
     enjoyed
    0.74
     recommended
    0.73
     recommend
    0.73
     spoilers
    0.72
     recommendation
    0.72
    enjoy
    0.70
    Act Density 0.316%

    No Known Activations