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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and code syntaxes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.83
     conclud
    -0.69
     labour
    -0.68
     trou
    -0.66
     therap
    -0.66
     fortun
    -0.65
     filmmaking
    -0.64
     Glock
    -0.63
     Outdoor
    -0.62
    arians
    -0.62
    POSITIVE LOGITS
    });
    1.07
    };
    1.02
    },
    0.99
    })
    0.97
     actionGroup
    0.92
    }{
    0.90
    }}
    0.86
    Static
    0.86
     Pwr
    0.85
    }
    0.84
    Act Density 0.244%

    No Known Activations