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

    Neuronpedia

    INDEX
    Explanations

    the repeated phrase "every single" followed by various nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing singularity or individual importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctr
    -0.77
    eln
    -0.73
    ello
    -0.73
    ÃĥÃĤ
    -0.67
    aba
    -0.67
     srfAttach
    -0.66
    orthy
    -0.65
    laden
    -0.64
    chi
    -0.64
    dor
    -0.63
    POSITIVE LOGITS
    THING
    1.08
     imaginable
    0.99
     conceivable
    0.90
     goddamn
    0.88
     facet
    0.88
    WHERE
    0.82
     inch
    0.80
     penny
    0.77
    grain
    0.76
     godd
    0.76
    Act Density 0.046%

    No Known Activations