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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to object-oriented code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hots
    -0.17
    chemistry
    -0.15
    ovel
    -0.14
    DED
    -0.14
    HAL
    -0.14
    ials
    -0.14
     Cheers
    -0.14
    alet
    -0.14
    -badge
    -0.14
    wg
    -0.14
    POSITIVE LOGITS
    elman
    0.18
    è¾°
    0.16
    berman
    0.15
     Eaton
    0.15
    .xz
    0.14
    (&_
    0.13
    814
    0.13
    583
    0.13
    980
    0.13
    erb
    0.13
    Act Density 0.002%

    No Known Activations