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

    Neuronpedia

    INDEX
    Explanations

    words related to setting, establishing, or creating something new or influential

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to setting standards or precedents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.74
    uman
    -0.66
    enza
    -0.64
    akening
    -0.63
     Terminal
    -0.59
    eral
    -0.59
     subp
    -0.58
    lees
    -0.58
    asso
    -0.58
    unte
    -0.57
    POSITIVE LOGITS
     precedent
    1.02
     abl
    0.99
     precedence
    0.99
    tle
    0.86
     sights
    0.84
    flame
    0.84
     groundwork
    0.82
     preced
    0.79
     aside
    0.75
     tone
    0.73
    Act Density 0.116%

    No Known Activations