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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the first name "Steve" or similar variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dia
    -0.66
    Þ
    -0.66
     births
    -0.64
     Duchess
    -0.63
     exting
    -0.63
    ailability
    -0.62
     Bahamas
    -0.61
    ĸļ士
    -0.60
    Topics
    -0.60
    =~=~
    -0.60
    POSITIVE LOGITS
    ophy
    0.77
    regor
    0.76
    redo
    0.73
    iven
    0.73
    ettel
    0.71
    aghan
    0.70
    Donnell
    0.70
    bert
    0.68
    shield
    0.68
    bard
    0.68
    Act Density 0.140%

    No Known Activations