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

    Neuronpedia

    INDEX
    Explanations

    expressions of curiosity or inquisitive thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swire
    -0.16
    bang
    -0.15
    witch
    -0.15
    lug
    -0.15
    _FAR
    -0.14
    ãĤŃãĥ³ãĤ°
    -0.14
    programming
    -0.14
    etak
    -0.14
    umas
    -0.14
    Sizer
    -0.14
    POSITIVE LOGITS
    825
    0.17
    HELL
    0.15
    ICI
    0.15
    401
    0.15
    Ñģклад
    0.14
    湯
    0.14
    riel
    0.14
    loyd
    0.14
     Meng
    0.14
    473
    0.13
    Act Density 0.004%

    No Known Activations