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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     we
    -0.61
     our
    -0.60
     μας
    -0.58
    กัน
    -0.57
     själva
    -0.56
     Our
    -0.56
     hearts
    -0.55
    ConstraintMaker
    -0.54
     ourselves
    -0.53
    Our
    -0.53
    POSITIVE LOGITS
     myself
    1.22
    myself
    0.95
     myſelf
    0.93
     Myself
    0.85
     my
    0.82
     ProtoMessage
    0.81
     moje
    0.80
     personalmente
    0.80
     nakalista
    0.75
    adaptiveStyles
    0.72
    Act Density 0.567%

    No Known Activations