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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "From."

    oai_token-act-pair · gpt-3.5-turbo

    references to the source or origin of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifling
    -0.77
    ratulations
    -0.70
    rongh
    -0.67
    isec
    -0.67
    faced
    -0.66
    ounces
    -0.66
    starter
    -0.65
    ometer
    -0.63
    priority
    -0.63
    rum
    -0.63
    POSITIVE LOGITS
     afar
    1.12
     whence
    1.11
     thence
    0.95
     Below
    0.89
     Above
    0.87
     Within
    0.79
     Across
    0.77
     Wow
    0.77
     Beginning
    0.72
     inside
    0.71
    Act Density 0.026%

    No Known Activations