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

    Neuronpedia

    INDEX
    Explanations

    adverbs expressing intensity or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the word "so" followed by expressions of intensity or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.73
    ulia
    -0.67
     eviction
    -0.63
    amac
    -0.62
    works
    -0.62
     coincides
    -0.62
    theless
    -0.61
     glances
    -0.60
     SHARES
    -0.59
     Flavoring
    -0.59
    POSITIVE LOGITS
    bered
    1.20
    ooo
    1.07
    oooo
    1.06
    oths
    1.02
    oooooooo
    1.01
    othes
    0.96
    zin
    0.91
    oooooooooooooooo
    0.91
     far
    0.86
    apy
    0.86
    Act Density 0.079%

    No Known Activations