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

    Neuronpedia

    INDEX
    Explanations

    words related to irreversibility

    oai_token-act-pair · gpt-3.5-turbo

    words beginning with the prefix "irre-"

    oai_token-act-pair · gpt-4-turbo

    terms related to irreparability and permanence in negative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.81
     Hunters
    -0.77
     Trials
    -0.75
    auri
    -0.72
    ramid
    -0.72
     Butterfly
    -0.70
    ucket
    -0.70
     Cosponsors
    -0.67
     Bureau
    -0.65
     Klu
    -0.64
    POSITIVE LOGITS
     irre
    1.26
    voc
    1.18
    parable
    0.93
    itable
    0.86
    ality
    0.84
    lev
    0.80
    hab
    0.80
    viation
    0.78
    agan
    0.76
    heat
    0.76
    Act Density 0.006%

    No Known Activations