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

    Neuronpedia

    INDEX
    Explanations

    verbs related to making projections or estimates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to predictions and forecasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    displayText
    -0.78
     Pastebin
    -0.73
    err
    -0.72
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.70
    SPONSORED
    -0.70
    youtube
    -0.66
    plom
    -0.65
    ãģĹ
    -0.64
    ILA
    -0.64
    rir
    -0.63
    POSITIVE LOGITS
     that
    0.95
     probabilities
    0.76
    phas
    0.72
     attendance
    0.72
     revenues
    0.71
     gradual
    0.71
     upwards
    0.71
     periods
    0.70
     maximum
    0.69
    that
    0.69
    Act Density 0.241%

    No Known Activations