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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements in centimeters

    oai_token-act-pair · gpt-3.5-turbo

    measurements in centimeters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":"","
    -0.76
    spell
    -0.70
    ggies
    -0.68
    iciary
    -0.67
    topic
    -0.64
    lez
    -0.63
    ceivable
    -0.62
     Homeland
    -0.60
    elines
    -0.60
     Jarrett
    -0.59
    POSITIVE LOGITS
     diameter
    0.95
    asonic
    0.81
    oses
    0.79
    ahon
    0.79
    jpg
    0.79
    illon
    0.78
    pieces
    0.77
    aj
    0.74
     thickness
    0.74
    obyl
    0.73
    Act Density 0.006%

    No Known Activations