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

    Neuronpedia

    INDEX
    Explanations

    action verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    verbs or phrases indicating ongoing actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kush
    -0.65
     disclosures
    -0.64
     Lies
    -0.61
     Gutenberg
    -0.60
     languages
    -0.58
     Shal
    -0.58
     Tinder
    -0.57
     Byr
    -0.57
     Lobby
    -0.57
     Hey
    -0.57
    POSITIVE LOGITS
    tnc
    0.80
    nih
    0.78
    MpServer
    0.76
    ');
    0.75
    ubes
    0.72
    >]
    0.72
    DCS
    0.71
    saf
    0.71
    ãĤ©
    0.70
    ibo
    0.68
    Act Density 0.417%

    No Known Activations