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

    Neuronpedia

    INDEX
    Explanations

    issues related to connectivity and performance in devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.48
    AndEndTag
    -0.46
    AnimationsModule
    -0.46
    RenderAtEndOf
    -0.43
    irvana
    -0.41
     flat
    -0.38
     świ
    -0.36
    hada
    -0.36
    VersionUID
    -0.36
    }{*}{
    -0.36
    POSITIVE LOGITS
     ripped
    1.09
     ripping
    1.04
     tearing
    1.03
     torn
    0.97
     rip
    0.92
     rips
    0.89
     tore
    0.89
     loosened
    0.85
     detach
    0.84
     tear
    0.83
    Act Density 0.712%

    No Known Activations