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

    Neuronpedia

    INDEX
    Explanations

    URLs and related web-related terminology

    oai_token-act-pair · gpt-3.5-turbo

    references to URLs and networked content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Afric
    -0.74
     Nigerian
    -0.63
    =]
    -0.63
     Luthor
    -0.62
     Nare
    -0.62
     Visa
    -0.58
     Verd
    -0.58
     Mub
    -0.58
     athlet
    -0.57
    arching
    -0.57
    POSITIVE LOGITS
    Anyway
    0.74
    mosp
    0.72
    assis
    0.67
    */(
    0.65
    saf
    0.64
    /(
    0.64
    Spell
    0.64
    weather
    0.64
    morrow
    0.63
    orbit
    0.63
    Act Density 0.512%

    No Known Activations