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

    Neuronpedia

    INDEX
    Explanations

    references to companies and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    979
    -0.16
    tes
    -0.15
    695
    -0.15
    129
    -0.15
    64
    -0.14
    zer
    -0.14
    889
    -0.14
    oro
    -0.14
    417
    -0.14
    ÑĨеÑĢ
    -0.14
    POSITIVE LOGITS
     effect
    0.16
    enberg
    0.16
    _effect
    0.16
    -effect
    0.16
    bbe
    0.16
    Unsafe
    0.15
    óng
    0.15
    unning
    0.14
    ,eg
    0.14
    vang
    0.14
    Act Density 0.006%

    No Known Activations