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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of approaching

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "approach" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pite
    -0.82
    cell
    -0.75
    gans
    -0.70
    marine
    -0.69
    glass
    -0.69
    inker
    -0.68
    rats
    -0.65
    multipl
    -0.65
    bel
    -0.64
    fre
    -0.64
    POSITIVE LOGITS
     Ceres
    0.78
     puberty
    0.69
     Lans
    0.66
    IDENT
    0.66
     heights
    0.65
    iddles
    0.65
    adata
    0.65
     adulthood
    0.64
    ADRA
    0.64
     nearer
    0.64
    Act Density 0.044%

    No Known Activations