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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themselves
    -0.79
     itself
    -0.68
     himself
    -0.67
     Himself
    -0.65
     herself
    -0.60
    themselves
    -0.56
     oneself
    -0.53
     Itself
    -0.53
     Yash
    -0.53
     fluid
    -0.52
    POSITIVE LOGITS
    zarchiwizowane
    0.61
    LLocation
    0.60
    WriteAttribute
    0.59
    клопе
    0.59
    لينكات
    0.57
    ()',
    0.56
    vière
    0.56
    adaptiveStyles
    0.55
     nästa
    0.55
    principalColumn
    0.54
    Act Density 0.231%

    No Known Activations