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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets with syntax related elements

    oai_token-act-pair · gpt-3.5-turbo

    representations of technical or programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leth
    -0.75
     Patron
    -0.75
     Vill
    -0.74
     Kes
    -0.74
     paran
    -0.73
     Weekly
    -0.72
     Mush
    -0.72
     Sau
    -0.71
     Scenes
    -0.71
     Café
    -0.71
    POSITIVE LOGITS
    /*
    1.31
    @@
    1.27
    };
    1.21
    //
    1.20
    /**
    1.18
    assert
    1.12
    ////////////////////////////////
    1.12
    DEBUG
    1.10
    &&
    1.10
    }
    1.08
    Act Density 0.085%

    No Known Activations