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

    Neuronpedia

    INDEX
    Explanations

    phrases and words that indicate likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    likelihood and probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -0.64
     ProtoMessage
    -0.59
     ModelExpression
    -0.57
     يتيمه
    -0.55
    -------
    -0.55
     jspb
    -0.55
    WebVitals
    -0.51
     propOrder
    -0.50
    findpost
    -0.49
    XmlAccessType
    -0.49
    POSITIVE LOGITS
     likely
    0.67
     probably
    0.66
    umably
    0.59
    probably
    0.59
    raisemb
    0.58
    mutlich
    0.57
     вероятно
    0.57
     kemungkinan
    0.56
     wahrscheinlich
    0.55
    arschijnlijk
    0.54
    Act Density 0.116%

    No Known Activations