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

    Neuronpedia

    INDEX
    Explanations

    the word "Caps" with varying levels of emphasis and contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "caps" and its variations, indicating a focus on themes related to sports or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galile
    -0.71
     Heist
    -0.68
    lder
    -0.65
    Bey
    -0.65
    proof
    -0.64
    bow
    -0.64
    Georg
    -0.63
     Fein
    -0.62
    spe
    -0.61
     Starr
    -0.61
    POSITIVE LOGITS
    ules
    1.19
    icum
    1.18
    aic
    1.09
    itals
    1.09
    itol
    1.06
    ule
    1.01
    acus
    0.92
    caps
    0.92
    uits
    0.91
    rison
    0.88
    Act Density 0.038%

    No Known Activations