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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anus
    -0.18
    men
    -0.15
    vt
    -0.14
    ofs
    -0.14
    usat
    -0.14
    ies
    -0.14
    opis
    -0.14
    270
    -0.13
    lec
    -0.13
    bies
    -0.13
    POSITIVE LOGITS
    ably
    0.23
    ned
    0.21
    auer
    0.21
    ation
    0.20
    edly
    0.18
    near
    0.18
    ingly
    0.16
    ificados
    0.16
    atively
    0.15
     near
    0.15
    Act Density 0.017%

    No Known Activations