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

    Neuronpedia

    INDEX
    Explanations

    percentages related to increases and decreases in various statistics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical increases and decreases in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     staples
    -0.64
    GES
    -0.58
    ALE
    -0.58
    PAR
    -0.55
     Monstrous
    -0.55
     muster
    -0.54
     Cabin
    -0.54
     Parables
    -0.54
    MET
    -0.54
     Purg
    -0.54
    POSITIVE LOGITS
    xual
    1.04
    over
    0.90
    onential
    0.82
    ulative
    0.78
     rate
    0.77
     subsequ
    0.76
    ivist
    0.75
    erence
    0.75
    itures
    0.75
    ait
    0.73
    Act Density 0.095%

    No Known Activations