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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional conflict and interpersonal complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.73
     himself
    -0.69
    InitVars
    -0.67
     @"/
    -0.65
     الدولى
    -0.64
    __":
    -0.60
    drawSprites
    -0.59
    iterraneo
    -0.59
     Himself
    -0.58
    himself
    -0.58
    POSITIVE LOGITS
     herself
    1.50
    herself
    1.09
     her
    1.00
     she
    0.96
     ihrem
    0.80
     hennes
    0.78
     ihren
    0.76
     shes
    0.74
     bint
    0.74
    她是
    0.74
    Act Density 0.308%

    No Known Activations