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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and symbols

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Glock
    -0.75
     Canal
    -0.74
     hooked
    -0.72
     abroad
    -0.71
     somew
    -0.69
     stewards
    -0.68
     Outdoor
    -0.67
     whistle
    -0.67
     reporting
    -0.67
     Hook
    -0.66
    POSITIVE LOGITS
    }}
    1.20
    });
    1.17
    lambda
    1.15
    }
    1.14
    }\
    1.12
    {\
    1.10
    })
    1.09
    },
    1.08
    _{
    1.08
    }{
    1.08
    Act Density 0.020%

    No Known Activations