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

    Neuronpedia

    INDEX
    Explanations

    text within special characters and numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistical representations within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paran
    -0.69
     Coffin
    -0.66
    unda
    -0.63
     Remote
    -0.62
     coffin
    -0.62
     Unsure
    -0.61
     vortex
    -0.61
    chuk
    -0.60
    ction
    -0.59
     totem
    -0.59
    POSITIVE LOGITS
    shall
    0.80
    onne
    0.76
    then
    0.75
    ³³³³³³³³³³³³³³³³
    0.74
    ï
    0.74
    lighting
    0.72
    according
    0.72
    lete
    0.71
    LESS
    0.70
    sed
    0.69
    Act Density 0.077%

    No Known Activations