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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitation or contextual boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥ³ãĥī
    -0.17
    udur
    -0.16
     Parade
    -0.14
    rels
    -0.14
     Parr
    -0.14
    icias
    -0.14
    uja
    -0.14
    variants
    -0.13
    erland
    -0.13
     Cout
    -0.13
    POSITIVE LOGITS
     GOODMAN
    0.14
    MBER
    0.14
    939
    0.14
    ushman
    0.14
    adele
    0.14
    atsby
    0.14
    ATIO
    0.14
    ãĥĵãĥ¼
    0.14
    rane
    0.14
    _UNUSED
    0.14
    Act Density 0.100%

    No Known Activations