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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating speculation or assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABS
    -0.15
    lf
    -0.15
    pter
    -0.15
    зв
    -0.14
    eph
    -0.14
    icky
    -0.14
    Sr
    -0.14
    Ã¶ÃŁe
    -0.14
    amos
    -0.13
    .populate
    -0.13
    POSITIVE LOGITS
    ]={↵
    0.16
    orie
    0.15
    inke
    0.15
    alue
    0.15
    .must
    0.14
    γει
    0.14
    SSIP
    0.14
    deo
    0.14
    /../
    0.14
    Wa
    0.14
    Act Density 0.141%

    No Known Activations