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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction or ending

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the substring 'st'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merce
    -0.85
    hound
    -0.82
    terness
    -0.75
    veyard
    -0.74
    prus
    -0.74
    hower
    -0.73
    EStream
    -0.73
    staking
    -0.73
    cules
    -0.72
    perty
    -0.71
    POSITIVE LOGITS
    oppers
    1.05
    amped
    1.02
    rict
    1.01
    alker
    1.01
    upid
    0.98
    alking
    0.93
    retch
    0.90
    ools
    0.89
    itched
    0.89
    oppable
    0.88
    Act Density 0.022%

    No Known Activations