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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating criticism or disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilst
    -0.23
    ally
    -0.15
    itan
    -0.14
    aden
    -0.14
    ilk
    -0.14
    EGA
    -0.14
    æĬĢ
    -0.14
    agal
    -0.13
    iron
    -0.13
    agen
    -0.13
    POSITIVE LOGITS
    jem
    0.17
    /WebAPI
    0.17
    otas
    0.17
    GuidId
    0.15
     epoch
    0.15
    canf
    0.15
    actionDate
    0.15
    imuth
    0.15
     lump
    0.14
    kd
    0.14
    Act Density 0.449%

    No Known Activations