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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    words related to individual identities or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spring
    -0.84
    matic
    -0.79
     maiden
    -0.72
    sets
    -0.67
    rises
    -0.66
    animous
    -0.65
    graph
    -0.64
    lime
    -0.62
    mable
    -0.61
    north
    -0.60
    POSITIVE LOGITS
    chnology
    1.29
    ete
    1.25
    eme
    1.01
    lements
    0.95
    uve
    0.91
    opol
    0.88
    zos
    0.85
    elist
    0.85
    anu
    0.83
    lde
    0.81
    Act Density 0.014%

    No Known Activations