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

    Neuronpedia

    INDEX
    Explanations

    medical conditions or procedures related to destruction or harm

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrences of the substring "st"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hound
    -0.86
    veyard
    -0.82
    staking
    -0.80
    cules
    -0.80
    merce
    -0.75
    perty
    -0.74
    hower
    -0.73
    terness
    -0.73
    EStream
    -0.73
    prus
    -0.72
    POSITIVE LOGITS
    oppers
    1.13
    rict
    1.06
    amped
    1.05
    alker
    1.02
    upid
    0.99
    alking
    0.98
    retch
    0.95
    uffed
    0.95
    ructure
    0.95
    ools
    0.94
    Act Density 0.031%

    No Known Activations