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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.83
    pire
    -0.78
    thren
    -0.77
    comes
    -0.75
    istic
    -0.75
    oru
    -0.72
    sterdam
    -0.71
    casters
    -0.69
    anooga
    -0.68
    istically
    -0.68
    POSITIVE LOGITS
     ILCS
    0.90
    LECT
    0.81
    estinal
    0.76
    803
    0.76
    dB
    0.75
    mph
    0.74
    131
    0.74
    653
    0.74
    595
    0.72
    wcsstore
    0.72
    Act Density 0.024%

    No Known Activations