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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and emotional responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /or
    -0.16
    abouts
    -0.15
     latter
    -0.15
    ington
    -0.14
    YPE
    -0.14
     '../../../../../
    -0.14
    ãĥ¥
    -0.13
     Dove
    -0.13
    nt
    -0.13
    ilver
    -0.13
    POSITIVE LOGITS
    ÑĢади
    0.17
    adio
    0.17
    apot
    0.16
    ibs
    0.16
    quier
    0.15
    éra
    0.15
    ecies
    0.15
    ubat
    0.15
    jad
    0.14
    uida
    0.14
    Act Density 0.196%

    No Known Activations