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

    Neuronpedia

    INDEX
    Explanations

    numeric or citation elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disillusion
    -0.77
     boredom
    -0.75
     exhaustion
    -0.70
     realism
    -0.67
     propri
    -0.64
     glimps
    -0.63
     Conf
    -0.63
     autonomy
    -0.62
     sarc
    -0.62
     hindsight
    -0.62
    POSITIVE LOGITS
    bsite
    0.77
    ァ
    0.76
    ンジ
    0.75
    ************
    0.74
    umerable
    0.74
    ة
    0.72
    ر
    0.72
    fty
    0.72
    ÍÍ
    0.70
    terday
    0.69
    Act Density 0.164%

    No Known Activations