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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events

    oai_token-act-pair · gpt-3.5-turbo

    key performance metrics and evaluative phrases related to events or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \">
    -0.58
    necessary
    -0.57
    ãģĹ
    -0.55
    ]+
    -0.55
     stimulating
    -0.55
    ãģĻ
    -0.54
    Interstitial
    -0.52
     Defendants
    -0.51
    addons
    -0.51
    akin
    -0.51
    POSITIVE LOGITS
     consisted
    1.16
     consists
    1.15
     involves
    1.14
     revolves
    1.05
     came
    1.03
     appears
    0.99
     was
    0.97
     comes
    0.97
     resides
    0.94
     arrives
    0.94
    Act Density 0.591%

    No Known Activations