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

    Neuronpedia

    INDEX
    Explanations

    words related to removal or exclusion

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of elimination or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.71
    soType
    -0.66
    dn
    -0.65
    wat
    -0.64
    felt
    -0.64
    ETS
    -0.64
     Nieto
    -0.64
    embed
    -0.63
    fab
    -0.63
    nan
    -0.62
    POSITIVE LOGITS
     altogether
    1.11
     redund
    0.92
     redundancy
    0.90
     duplication
    0.89
     entirely
    0.86
     prejudice
    0.84
     outright
    0.83
     needless
    0.82
     loopholes
    0.80
     superflu
    0.77
    Act Density 0.067%

    No Known Activations