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

    Neuronpedia

    INDEX
    Explanations

    references to ghosts or spectral themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.87
    IndentedString
    -0.83
    contentLoaded
    -0.78
    __':
    -0.77
    دانشنامهٔ
    -0.77
     ddelweddau
    -0.76
     beginnetje
    -0.74
     nahilalakip
    -0.74
     HttpNotFound
    -0.73
    Hentet
    -0.73
    POSITIVE LOGITS
     possess
    0.60
     drift
    0.58
    ↵↵
    0.58
    ns
    0.57
     Hartman
    0.55
    حق
    0.54
     possesses
    0.54
     Cline
    0.52
     rumours
    0.52
     possessed
    0.51
    Act Density 0.090%

    No Known Activations