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

    Neuronpedia

    INDEX
    Explanations

    visual references or figures in academic writing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.86
     Roskov
    -0.81
    UnsafeEnabled
    -0.80
    ьаж
    -0.77
    WriteBarrier
    -0.76
    ArrowToggle
    -0.76
     propOrder
    -0.75
     مشين
    -0.74
    ंदीखरीदारी
    -0.74
    demment
    -0.74
    POSITIVE LOGITS
    <bos>
    0.56
    IBinder
    0.56
    ManagedBean
    0.40
     haf
    0.39
    retweeted
    0.39
    postdata
    0.39
    HttpSession
    0.38
     Introduction
    0.38
    say
    0.38
    MediaPlayer
    0.38
    Act Density 0.918%

    No Known Activations