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

    Neuronpedia

    INDEX
    Explanations

    words related to citing or referencing sources or information

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with referencing, highlighting, and citing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.77
    ctors
    -0.76
    knit
    -0.73
    quer
    -0.69
    cele
    -0.69
    kie
    -0.68
    cum
    -0.67
    soever
    -0.67
    ni
    -0.66
    window
    -0.66
    POSITIVE LOGITS
     inconsistencies
    0.70
     extensively
    0.70
     prominently
    0.69
    WER
    0.69
     passages
    0.67
     excerpts
    0.66
     urgency
    0.66
    phas
    0.66
     suggestions
    0.65
     phrases
    0.63
    Act Density 0.158%

    No Known Activations