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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with two words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consolid
    -0.63
     disadvantaged
    -0.62
     deleg
    -0.61
     otherwise
    -0.61
     theirs
    -0.60
     realistically
    -0.59
     economically
    -0.59
     supplemented
    -0.59
     reserv
    -0.59
     subdiv
    -0.58
    POSITIVE LOGITS
     Revenge
    1.06
    kaya
    1.01
     Daughter
    0.97
    wered
    0.94
    niper
    0.93
     Choice
    0.92
    arah
    0.92
    ullivan
    0.90
     Latest
    0.89
    keleton
    0.88
    Act Density 0.133%

    No Known Activations