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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word 'Prom' and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to promises or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palmer
    -0.71
    lihood
    -0.66
    gerald
    -0.66
    SEE
    -0.65
    RESULTS
    -0.64
    ARS
    -0.63
    Reviewer
    -0.63
     count
    -0.63
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.61
    RAFT
    -0.61
    POSITIVE LOGITS
    inent
    1.23
    otions
    1.22
    inently
    1.21
    etheus
    1.20
    otional
    1.18
    inence
    1.13
    oter
    1.08
    ises
    1.05
    oters
    0.95
    posal
    0.95
    Act Density 0.011%

    No Known Activations