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

    Neuronpedia

    INDEX
    Explanations

    verbs related to exerting influence or control over others

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to actions and behaviors that imply control or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eele
    -0.61
    duration
    -0.60
     respectively
    -0.57
     Various
    -0.57
    ortment
    -0.56
    ciplinary
    -0.55
    opens
    -0.55
     assortment
    -0.55
    dozen
    -0.55
     undoubtedly
    -0.54
    POSITIVE LOGITS
     anymore
    1.34
     anything
    1.09
     anybody
    1.06
     any
    1.00
     ANY
    0.94
     nor
    0.94
     anyone
    0.92
     them
    0.78
     anywhere
    0.78
     him
    0.77
    Act Density 0.403%

    No Known Activations