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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    didSet
    -0.71
     }}$}
    -0.69
    xase
    -0.68
    spill
    -0.62
    Explicación
    -0.59
    uyện
    -0.59
    '],
    -0.59
    SPATH
    -0.58
    hadiran
    -0.58
     للاسماء
    -0.57
    POSITIVE LOGITS
    vum
    0.56
    !
    0.51
    phosa
    0.51
    mergeFrom
    0.49
     Insee
    0.48
     Afraid
    0.46
    щення
    0.44
     this
    0.44
    AnimationsModule
    0.43
     mentales
    0.43
    Act Density 0.614%

    No Known Activations