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

    Neuronpedia

    INDEX
    Explanations

    adjectives or descriptors representing negative characteristics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases related to continuity and complexity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.79
     Jury
    -0.77
    uckland
    -0.73
     ende
    -0.70
    etsk
    -0.68
    hyde
    -0.66
    ertodd
    -0.66
    aukee
    -0.66
     Shed
    -0.64
    ersen
    -0.64
    POSITIVE LOGITS
    votes
    0.88
     proportions
    0.74
    activity
    0.70
     goodies
    0.66
     contradictions
    0.63
    isations
    0.63
     goodness
    0.62
     pills
    0.62
     exclus
    0.62
     icons
    0.62
    Act Density 0.465%

    No Known Activations