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

    Neuronpedia

    INDEX
    Explanations

    references to publications and their citation formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.55
    ']['
    -0.53
     nguy
    -0.51
    RemindMe
    -0.49
     '../../
    -0.47
     sport
    -0.46
     [](
    -0.46
    nord
    -0.45
    ();
    -0.45
    InitVars
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.71
    CrossRef
    0.70
    ValueStyle
    0.67
     GenerationType
    0.66
    +#+
    0.60
     Wallflower
    0.60
    enderror
    0.59
    مصادر
    0.58
     parch
    0.58
    getWriter
    0.58
    Act Density 0.298%

    No Known Activations