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

    Neuronpedia

    INDEX
    Explanations

    phrases related to features or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent features and themes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     to
    -0.66
    earchers
    -0.63
     intending
    -0.62
     by
    -0.62
     intentionally
    -0.55
    ufact
    -0.55
     voluntarily
    -0.53
     conditional
    -0.53
     whereby
    -0.52
     allowing
    -0.51
    POSITIVE LOGITS
    \":
    0.98
    )?
    0.89
    .?
    0.88
    .ãĢį
    0.84
    )}
    0.80
    .</
    0.78
    .#
    0.78
    ''.
    0.78
    },"
    0.77
    .—
    0.77
    Act Density 1.056%

    No Known Activations