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

    Neuronpedia

    INDEX
    Explanations

    references to specific demographic information and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achs
    -0.16
    olla
    -0.15
    avra
    -0.15
    oust
    -0.15
    ij¸
    -0.14
    Æ°Æ¡
    -0.14
    ettle
    -0.14
    SEL
    -0.14
    erras
    -0.14
    odka
    -0.14
    POSITIVE LOGITS
     um
    0.15
     Pf
    0.14
     present
    0.14
     coaching
    0.14
     him
    0.14
     Um
    0.14
     release
    0.14
    woord
    0.13
    æĤŁ
    0.13
    elerin
    0.13
    Act Density 0.050%

    No Known Activations