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

    Neuronpedia

    INDEX
    Explanations

    special format characters and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    —
    -0.60
     „
    -0.58
    cur
    -0.51
     $(\
    -0.51
     $\
    -0.51
     ${
    -0.50
     فريبيس
    -0.50
    \_
    -0.49
    wend
    -0.49
    ญิง
    -0.48
    POSITIVE LOGITS
    
    3.97
    
    2.56
    
    2.29
    .
    2.28
     
    2.13
    #
    1.69
    /*
    1.52
    /**
    1.52
    //
    1.44
    <?
    1.12
    Act Density 0.084%

    No Known Activations