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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing or emphasizing a specific idea or concept

    oai_token-act-pair · gpt-3.5-turbo

    expressions of collective experiences or shared sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sequ
    -0.72
    astical
    -0.65
    ournal
    -0.65
    rics
    -0.62
    icio
    -0.61
    orious
    -0.61
    orio
    -0.60
    claimed
    -0.60
    rities
    -0.59
    acies
    -0.57
    POSITIVE LOGITS
    liest
    0.70
    ioch
    0.69
    SourceFile
    0.66
     longest
    0.65
    _-_
    0.65
     behav
    0.64
    phal
    0.61
     exorc
    0.60
    hest
    0.59
    Alias
    0.58
    Act Density 0.292%

    No Known Activations