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

    Neuronpedia

    INDEX
    Explanations

    elements related to dangerous actions or stunts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     str
    -0.53
     based
    -0.51
     base
    -0.49
    อม
    -0.49
    baomidou
    -0.48
    patri
    -0.46
    thun
    -0.46
     past
    -0.46
    ത്ത
    -0.45
     depending
    -0.44
    POSITIVE LOGITS
     suspendu
    0.71
    DockStyle
    0.71
     esternos
    0.70
    IntoConstraints
    0.70
    
    0.70
    сылкі
    0.69
    BeginInit
    0.69
    Skocz
    0.68
    BufferException
    0.68
    RenderAtEndOf
    0.68
    Act Density 0.200%

    No Known Activations