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

    Neuronpedia

    INDEX
    Explanations

    specific references and actions related to events or situations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.73
    alian
    -0.69
    ctic
    -0.67
    anchester
    -0.67
    thal
    -0.65
    hew
    -0.65
    orts
    -0.65
    fal
    -0.64
    eme
    -0.63
    ista
    -0.63
    POSITIVE LOGITS
     namely
    1.25
     Towards
    0.69
     Convers
    0.67
     Revenge
    0.65
     Fountain
    0.64
     Return
    0.63
     Something
    0.62
     Cosmos
    0.62
     TED
    0.61
    ITT
    0.61
    Act Density 0.209%

    No Known Activations