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

    Neuronpedia

    INDEX
    Explanations

    words related to disturbance or disruption

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty content or lack of meaningful text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reborn
    -0.80
     Shepherd
    -0.79
     Worlds
    -0.79
     Madness
    -0.77
     Companion
    -0.77
     Handbook
    -0.76
     Wol
    -0.76
     Warriors
    -0.75
     Enlightenment
    -0.75
     Leilan
    -0.73
    POSITIVE LOGITS
    secut
    1.10
    withstanding
    1.08
    tenance
    1.07
    acters
    1.07
    arently
    1.06
    abor
    1.05
    unte
    1.05
    reprene
    1.03
    yright
    1.03
    actly
    1.00
    Act Density 0.252%

    No Known Activations