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

    Neuronpedia

    INDEX
    Explanations

    elements related to specific actions and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eyim
    -0.15
    apan
    -0.15
    uros
    -0.14
    avanaugh
    -0.14
    /tiny
    -0.14
    enko
    -0.14
    eros
    -0.14
    ight
    -0.14
    Cause
    -0.14
    /msg
    -0.14
    POSITIVE LOGITS
    oba
    0.14
     religion
    0.14
    .Ct
    0.14
    ipple
    0.14
    ľ
    0.14
    ÏĪη
    0.14
    lep
    0.13
     Glyph
    0.13
    xffffffff
    0.13
     tapi
    0.13
    Act Density 0.050%

    No Known Activations