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

    Neuronpedia

    INDEX
    Explanations

    titles and references of various entities such as companies, movies, and people

    oai_token-act-pair · gpt-3.5-turbo

    references to titles of works or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mould
    -0.64
    ccording
    -0.63
     loft
    -0.61
    »Ĵ
    -0.59
     mosqu
    -0.56
     anchored
    -0.55
     ensu
    -0.55
     tremend
    -0.54
    ĸļ士
    -0.53
    everal
    -0.53
    POSITIVE LOGITS
    }.
    1.24
    .]
    1.12
    .''.
    0.99
    _.
    0.97
    >.
    0.97
    .}
    0.95
    ().
    0.95
    .</
    0.95
    };
    0.95
    ].
    0.94
    Act Density 0.837%

    No Known Activations