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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversational interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tonight
    -0.19
     hopefully
    -0.18
    Tonight
    -0.18
     Tonight
    -0.17
    hopefully
    -0.17
    Hopefully
    -0.16
    okable
    -0.15
     Hopefully
    -0.15
     lately
    -0.15
    Responder
    -0.14
    POSITIVE LOGITS
     PureComponent
    0.17
     during
    0.17
     Liter
    0.16
     literally
    0.15
    quit
    0.15
    maal
    0.15
     durante
    0.15
     ëĭ¹ìĭľ
    0.14
    Initially
    0.14
    ever
    0.14
    Act Density 0.211%

    No Known Activations