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

    Neuronpedia

    INDEX
    Explanations

    the name "Zabludovsky"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "able."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eve
    -0.88
    ORGE
    -0.82
    meal
    -0.70
    lli
    -0.68
    nor
    -0.68
     Catalyst
    -0.66
    birth
    -0.66
    women
    -0.66
    IDA
    -0.63
    PASS
    -0.63
    POSITIVE LOGITS
    anca
    1.29
    abl
    1.12
    anches
    0.94
    eness
    0.92
    osure
    0.89
    ingu
    0.88
    acas
    0.86
    ocaly
    0.84
    ocal
    0.82
    oom
    0.81
    Act Density 0.010%

    No Known Activations