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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    substack
    -0.74
    /#{
    -0.67
    /*
    -0.66
    //
    -0.65
    ]='\
    -0.64
    oudoune
    -0.64
     Ανακτήθηκε
    -0.60
    \\
    -0.60
    czuk
    -0.60
    ')['
    -0.59
    POSITIVE LOGITS
    endphp
    0.82
    </em>
    0.75
     ligiloj
    0.74
    MemoryWarning
    0.69
    rfloor
    0.68
    Demografie
    0.66
    Kjelder
    0.62
    กัน
    0.59
    nocache
    0.59
     saites
    0.57
    Act Density 0.940%

    No Known Activations