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

    Neuronpedia

    INDEX
    Explanations

    modal verbs related to future actions and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ×
    -0.44
    –
    -0.41
    aparte
    -0.41
    chained
    -0.41
    air
    -0.40
    <bos>
    -0.40
     doInBackground
    -0.40
    ویت
    -0.40
    彰
    -0.39
     mir
    -0.38
    POSITIVE LOGITS
    tableFuture
    0.79
    saraba
    0.77
     Référence
    0.70
    struts
    0.69
    openhague
    0.67
    ValueGenerated
    0.67
    IVEREF
    0.65
     Cię
    0.65
     Hvis
    0.64
     definately
    0.64
    Act Density 0.204%

    No Known Activations