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

    Neuronpedia

    INDEX
    Explanations

    issues related to race and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.55
     Pingback
    -0.50
    withstanding
    -0.48
    ouz
    -0.48
    ։
    -0.47
    ResumeLayout
    -0.47
    kenstock
    -0.47
     mView
    -0.46
    ">//
    -0.46
    lden
    -0.46
    POSITIVE LOGITS
     thì
    0.96
     فإن
    0.95
     maka
    0.78
    则
    0.78
     oprot
    0.69
     незавершена
    0.68
     they
    0.68
     there
    0.67
    則
    0.66
     it
    0.65
    Act Density 0.634%

    No Known Activations