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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code syntax

    oai_token-act-pair · gpt-3.5-turbo

    semicolon and parentheses in code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noxious
    -0.69
    bledon
    -0.67
    due
    -0.66
    ays
    -0.65
    ensibly
    -0.65
    shaw
    -0.64
    Tube
    -0.64
    cuts
    -0.63
    landish
    -0.63
    din
    -0.62
    POSITIVE LOGITS
     /*
    1.34
     };
    1.34
     //
    1.30
     }
    1.29
     /**
    1.16
     });
    1.16
    //
    1.10
    };
    1.07
     var
    1.05
     Console
    1.02
    Act Density 0.021%

    No Known Activations