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

    Neuronpedia

    INDEX
    Explanations

    terms associated with exclusion or avoidance of negative elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.72
    RenderAtEndOf
    -0.71
     AssemblyProduct
    -0.69
    ForRow
    -0.61
    astéroïdes
    -0.61
     pleaſure
    -0.57
     purpoſe
    -0.57
     Jefus
    -0.57
    onAttach
    -0.57
     chofe
    -0.56
    POSITIVE LOGITS
     any
    0.63
     никаких
    0.56
    geld
    0.54
    至於
    0.53
     no
    0.53
     bez
    0.52
     оригіналу
    0.52
     without
    0.52
    至于
    0.51
     unlike
    0.51
    Act Density 0.554%

    No Known Activations