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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusion or prohibition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to exclusion or staying away from certain people, places, or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elf
    -1.05
    ELS
    -0.71
    IZE
    -0.71
    ilib
    -0.65
    olars
    -0.63
    oria
    -0.62
    Scene
    -0.61
     antioxid
    -0.61
    iov
    -0.61
    ternity
    -0.60
    POSITIVE LOGITS
    nit
    0.80
     IPM
    0.66
    ned
    0.66
     bother
    0.66
     Avenger
    0.64
    411
    0.63
     ãĤµ
    0.63
    vana
    0.63
     altogether
    0.63
     Pryor
    0.63
    Act Density 0.051%

    No Known Activations