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

    Neuronpedia

    INDEX
    Explanations

    technical or programming-related terms and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psz
    -0.15
    roids
    -0.14
    amura
    -0.14
    odge
    -0.14
     Shak
    -0.13
    ugar
    -0.13
    ws
    -0.13
    .learning
    -0.13
    _fix
    -0.13
    WS
    -0.13
    POSITIVE LOGITS
    bud
    0.18
     bud
    0.16
    errick
    0.15
    arten
    0.14
     major
    0.14
     ÑģобоÑİ
    0.14
    ebi
    0.14
    cheng
    0.14
     Graz
    0.14
    itest
    0.14
    Act Density 0.009%

    No Known Activations