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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers reminiscent of numerical data

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values related to measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.83
    iard
    -0.77
    geist
    -0.77
    yang
    -0.73
    hner
    -0.73
    LOAD
    -0.70
    gement
    -0.70
    ei
    -0.70
    hare
    -0.70
    phas
    -0.69
    POSITIVE LOGITS
     ILCS
    1.25
    %:
    0.83
    ERSON
    0.82
    ISH
    0.79
    ishing
    0.77
    rican
    0.76
    liest
    0.74
    ENCY
    0.73
     Yard
    0.72
    RET
    0.72
    Act Density 0.095%

    No Known Activations