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

    Neuronpedia

    INDEX
    Explanations

    API-related terminologies and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }],
    -0.46
    complexContent
    -0.45
    prefixer
    -0.40
    <>();
    -0.39
     yet
    -0.39
    ），
    -0.38
    yet
    -0.38
    таратура
    -0.36
    '),
    -0.35
    )++;
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.55
     ResponseEntity
    0.52
    Autoritní
    0.45
    MVH
    0.44
    esez
    0.43
     rewarding
    0.42
     Italijanski
    0.41
    ætte
    0.41
    ########.
    0.41
    #+#
    0.40
    Act Density 0.229%

    No Known Activations