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

    Neuronpedia

    INDEX
    Explanations

    words that are related to criticism or blame

    oai_token-act-pair · gpt-3.5-turbo

    words related to blame or blaming actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ETF
    -0.69
    Construct
    -0.66
    reon
    -0.64
     Mai
    -0.63
    AGE
    -0.62
     Gould
    -0.62
    ÃįÃį
    -0.59
     Scholar
    -0.59
     Deity
    -0.58
    AGES
    -0.58
    POSITIVE LOGITS
    ossom
    1.34
    izzard
    1.23
    ameless
    1.17
    oat
    1.12
    anks
    1.12
    urring
    1.10
    adders
    1.08
    anche
    1.08
    anch
    1.08
    ithe
    1.07
    Act Density 0.011%

    No Known Activations