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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    assertions of clarity or certainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rella
    -0.85
    eport
    -0.80
    uese
    -0.79
    aily
    -0.78
    ntil
    -0.76
    oleon
    -0.72
    enaries
    -0.71
    awaru
    -0.70
    sembly
    -0.69
    nesota
    -0.69
    POSITIVE LOGITS
     deline
    1.11
     marked
    0.95
     identifiable
    0.92
     differentiated
    0.91
     distinguish
    0.91
     communicated
    0.82
     differentiate
    0.81
     articulated
    0.81
     labelled
    0.80
     indicated
    0.78
    Act Density 0.029%

    No Known Activations