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

    Neuronpedia

    INDEX
    Explanations

    phrases related to forward-thinking or planning for the future

    oai_token-act-pair · gpt-3.5-turbo

    terms related to future-oriented actions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seys
    -0.79
    ulhu
    -0.77
    ucket
    -0.76
    oyal
    -0.75
    ById
    -0.73
    soDeliveryDate
    -0.67
     Loaded
    -0.65
    minus
    -0.64
    angelo
    -0.63
    bath
    -0.62
    POSITIVE LOGITS
    enment
    0.96
    enium
    0.81
    Ô
    0.72
    WARD
    0.72
     motions
    0.65
     direction
    0.64
     advancement
    0.64
    wards
    0.63
     Destination
    0.61
     directions
    0.61
    Act Density 0.315%

    No Known Activations