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

    Neuronpedia

    INDEX
    Explanations

    percentage values expressed with a percentage sign

    oai_token-act-pair · gpt-3.5-turbo

    percentages related to rarity and commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     compan
    -0.83
     neighb
    -0.79
    pecially
    -0.77
     shaped
    -0.77
     lett
    -0.74
     thous
    -0.74
     showc
    -0.70
    itiz
    -0.70
    rament
    -0.70
     obser
    -0.70
    POSITIVE LOGITS
    -+
    0.79
    steamapps
    0.72
    ³³³³
    0.72
     Mehran
    0.71
    âĨij
    0.69
    !/
    0.68
    %-
    0.68
    oyer
    0.68
    lein
    0.68
    /-
    0.66
    Act Density 0.043%

    No Known Activations