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

    Neuronpedia

    INDEX
    Explanations

    assertions about personal beliefs and experiences

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

    personal states and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themſelves
    -0.77
     itſelf
    -0.65
     themselves
    -0.61
     فريبيس
    -0.61
     himſelf
    -0.56
     ainfi
    -0.54
    日閲覧
    -0.51
    themselves
    -0.50
    他們的
    -0.50
    ectoria
    -0.49
    POSITIVE LOGITS
     myself
    0.76
    myself
    0.61
     my
    0.60
     Myself
    0.58
     I
    0.53
     meinem
    0.49
    Myself
    0.48
     meine
    0.48
     minhas
    0.48
     meinen
    0.46
    Act Density 0.088%

    No Known Activations