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

    Neuronpedia

    INDEX
    Explanations

    programming functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orgh
    -0.18
    転
    -0.14
     accumulating
    -0.14
     stap
    -0.14
    rum
    -0.14
    ½Ķ
    -0.14
    mlink
    -0.13
    ειο
    -0.13
     accum
    -0.13
    razil
    -0.13
    POSITIVE LOGITS
    iese
    0.15
    ibri
    0.15
     Arist
    0.14
    uat
    0.14
    gi
    0.14
    gar
    0.14
    åĢ
    0.14
     Derrick
    0.14
    ast
    0.13
    íĥķ
    0.13
    Act Density 0.143%

    No Known Activations