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

    Neuronpedia

    INDEX
    Explanations

    words related to superlatives or extremes

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.75
    EStream
    -0.74
     shrink
    -0.71
    ļéĨĴ
    -0.70
     Lumpur
    -0.69
     proverb
    -0.67
    ulhu
    -0.65
     Hann
    -0.64
    »Ĵ
    -0.63
    Ń·
    -0.63
    POSITIVE LOGITS
    purpose
    1.11
    season
    1.07
    important
    1.04
    winner
    1.02
    around
    0.99
    party
    0.96
    together
    0.96
    consuming
    0.95
    star
    0.95
    sided
    0.93
    Act Density 0.026%

    No Known Activations