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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or events occurring

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating inaction or failure to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.84
    Dialogue
    -0.76
    ilus
    -0.73
    tnc
    -0.71
    pmwiki
    -0.68
    ammu
    -0.66
    undrum
    -0.66
    iaz
    -0.65
    hub
    -0.65
    nis
    -0.64
    POSITIVE LOGITS
     enough
    0.84
     sufficiently
    0.81
     adequately
    0.81
     slightest
    0.78
     sufficient
    0.72
     anymore
    0.71
     nor
    0.70
     adequate
    0.69
     quite
    0.69
     beforehand
    0.68
    Act Density 0.264%

    No Known Activations