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

    Neuronpedia

    INDEX
    Explanations

    excerpts related to interpersonal relationships and emotional interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ourselves
    -0.54
    …
    -0.47
     рам
    -0.47
     …
    -0.45
    相互
    -0.45
     ef
    -0.45
     staan
    -0.42
    กัน
    -0.42
     juntas
    -0.41
    astéro
    -0.41
    POSITIVE LOGITS
     himſelf
    1.03
     Theſe
    1.01
    SharedDtor
    0.94
     himself
    0.90
     Efq
    0.89
     itſelf
    0.81
     herself
    0.79
    principalColumn
    0.79
     chofe
    0.79
    ArgsConstructor
    0.78
    Act Density 1.067%

    No Known Activations