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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or new development

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time or recent developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Provided
    -0.68
    Reviewer
    -0.64
     tur
    -0.61
     Actions
    -0.60
    Redd
    -0.60
    sold
    -0.60
    Syn
    -0.59
    ãĥ³ãĤ¸
    -0.59
    warm
    -0.59
     Cosponsors
    -0.58
    POSITIVE LOGITS
    ences
    0.82
    ence
    0.76
    cation
    0.72
     confines
    0.72
     onward
    0.72
    geries
    0.71
    ulence
    0.67
    emetery
    0.66
     onwards
    0.64
    ENCE
    0.63
    Act Density 0.094%

    No Known Activations