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

    Neuronpedia

    INDEX
    Explanations

    predictions or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.67
    akers
    -0.66
    rency
    -0.64
     Enhancement
    -0.63
    usha
    -0.63
    avis
    -0.58
    ologue
    -0.58
     Named
    -0.58
     performing
    -0.58
    vis
    -0.58
    POSITIVE LOGITS
     happen
    1.25
     mean
    1.22
     imply
    1.01
     entail
    1.00
     translate
    0.99
     explain
    0.98
    mean
    0.98
     horr
    0.92
     result
    0.91
     means
    0.91
    Act Density 0.131%

    No Known Activations