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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating expectations or estimations of future events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to predictions or anticipated outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rehens
    -0.67
    tein
    -0.62
    brush
    -0.57
    earch
    -0.55
    ZI
    -0.52
     Secrets
    -0.51
    think
    -0.51
    conservancy
    -0.50
    orno
    -0.50
    AMA
    -0.49
    POSITIVE LOGITS
     to
    1.15
    to
    0.78
    To
    0.66
     soon
    0.64
    soDeliveryDate
    0.64
     To
    0.61
     sometime
    0.61
     TO
    0.60
    ologically
    0.59
    llor
    0.58
    Act Density 0.053%

    No Known Activations