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

    Neuronpedia

    INDEX
    Explanations

    discussions about quality, evaluation, and the contrast between easy and hard experiences or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idon
    -0.15
    agina
    -0.15
    ically
    -0.15
    elize
    -0.15
    alion
    -0.14
    ossal
    -0.14
    allas
    -0.14
     CAPITAL
    -0.14
    podob
    -0.14
    apons
    -0.14
    POSITIVE LOGITS
     ones
    0.18
     getVersion
    0.17
    lest
    0.17
     parts
    0.16
     version
    0.16
    chy
    0.16
     Version
    0.16
     Parts
    0.16
    éĥ¨åĪĨ
    0.15
     variety
    0.15
    Act Density 0.269%

    No Known Activations