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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ang
    -0.54
     Steen
    -0.54
     trans
    -0.51
     years
    -0.51
     pick
    -0.50
     in
    -0.50
    reno
    -0.49
     time
    -0.47
     queer
    -0.47
    슬
    -0.47
    POSITIVE LOGITS
    }})
    1.33
    }}},
    1.28
    }))
    1.25
    }])
    1.24
    }}}}
    1.24
    }}}
    1.23
    }_
    1.23
    }}_
    1.22
    }}}\
    1.22
    )}_
    1.22
    Act Density 0.561%

    No Known Activations