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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to comparisons or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixel
    -0.17
    woff
    -0.15
    ãĥĨãĤ£
    -0.14
    odom
    -0.13
     Til
    -0.13
    anth
    -0.13
    ÙĨØ´
    -0.13
     Hundred
    -0.13
    utherland
    -0.13
    Ĵ
    -0.13
    POSITIVE LOGITS
    hire
    0.14
     deserved
    0.14
     YaÅŁ
    0.13
    wise
    0.13
    singleton
    0.13
    echa
    0.13
     fewer
    0.13
     impart
    0.13
     tension
    0.13
     deserve
    0.13
    Act Density 0.059%

    No Known Activations