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

    Neuronpedia

    INDEX
    Explanations

    words related to recording, such as record, records, recording

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "record" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hiro
    -0.76
    gypt
    -0.74
    nen
    -0.74
     Leone
    -0.72
    hler
    -0.71
    ggles
    -0.66
    osi
    -0.66
     pneum
    -0.66
    chy
    -0.65
    apa
    -0.65
    POSITIVE LOGITS
    record
    0.89
    keeping
    0.88
     Record
    0.87
     record
    0.85
     Keeper
    0.82
    recorded
    0.81
     Holder
    0.80
     holder
    0.78
     records
    0.78
    downs
    0.76
    Act Density 0.025%

    No Known Activations