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

    Neuronpedia

    INDEX
    Explanations

    numerical comparisons indicating a higher value

    oai_token-act-pair · gpt-3.5-turbo

    words indicating age or level thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \/\/
    -0.69
     Fairfax
    -0.69
     Moff
    -0.66
     Tup
    -0.66
     Savannah
    -0.64
     TN
    -0.63
    tes
    -0.61
     Complex
    -0.61
     Nashville
    -0.59
     COP
    -0.58
    POSITIVE LOGITS
     thereof
    0.76
    .}
    0.75
     thereto
    0.72
    rongh
    0.71
     extraord
    0.70
    etheless
    0.68
     onwards
    0.65
     reborn
    0.65
     respectively
    0.64
    odi
    0.64
    Act Density 0.171%

    No Known Activations