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

    Neuronpedia

    INDEX
    Explanations

    quoted speech and expressions of excitement or enthusiasm

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

    Quoted text about positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    positive sentiment statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    THEN
    -0.59
     dunno
    -0.58
     sometimes
    -0.56
     wondering
    -0.53
    Frage
    -0.53
     question
    -0.52
     GenerationType
    -0.52
     hypothetical
    -0.52
     Frage
    -0.52
    Enllaços
    -0.52
    POSITIVE LOGITS
    Congratulations
    0.77
     Congratulations
    0.76
     delighted
    0.68
     I
    0.63
    nocześnie
    0.63
     thrilled
    0.61
     congratulations
    0.60
    今回の
    0.59
    Together
    0.58
     Excited
    0.58
    Act Density 0.062%

    No Known Activations