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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in a specific format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -4.06
    ⓧ
    -1.32
    <?
    -1.29
     intersper
    -1.11
    /**
    -1.08
    
    -1.07
     springfox
    -1.07
    /***
    -1.02
     disbur
    -1.00
     gratify
    -0.96
    POSITIVE LOGITS
     seksi
    0.71
     ';
    0.65
     vasi
    0.64
     corrom
    0.63
    {}".
    0.62
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.62
    ()")
    0.61
     mikrofon
    0.61
     marea
    0.60
     parati
    0.60
    Act Density 0.209%

    No Known Activations