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

    Neuronpedia

    INDEX
    Explanations

    sequences with number values

    oai_token-act-pair · gpt-3.5-turbo

    spaces or sequences of whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anyon
    -0.76
    OHN
    -0.74
     McMaster
    -0.67
    ylum
    -0.65
    ochet
    -0.62
    leground
    -0.62
    earchers
    -0.62
    gc
    -0.62
    cair
    -0.61
    alyst
    -0.61
    POSITIVE LOGITS
    3.63
     Âł
    2.56
    Âł
    2.41
     ³³
    2.14
     Âł Âł
    2.09
    ³³
    1.94
     Âł Âł Âł Âł
    1.88
    ↵Âł
    1.86
     Âł Âł Âł Âł Âł Âł Âł Âł
    1.81
    ³³³³³³³³
    1.64
    Act Density 0.010%

    No Known Activations