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

    Neuronpedia

    INDEX
    Explanations

    decimal numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.65
     cla
    -0.65
     mistrust
    -0.63
     tranquil
    -0.63
     herself
    -0.61
    Quantity
    -0.59
     psychiatrist
    -0.59
     Ellis
    -0.58
    ĸļ
    -0.57
     secrecy
    -0.57
    POSITIVE LOGITS
    GHz
    0.80
    rencies
    0.78
    peat
    0.78
     OD
    0.78
    ilver
    0.76
    iev
    0.76
    thren
    0.71
    ateral
    0.69
    thodox
    0.69
    handled
    0.69
    Act Density 0.254%

    No Known Activations