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

    Neuronpedia

    INDEX
    Explanations

    assertions related to identity and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.89
    CloseOperation
    -0.83
     виправивши
    -0.81
     pinulongan
    -0.80
     bezeichneter
    -0.79
    AsUp
    -0.76
    ungkin
    -0.75
    +#+#
    -0.74
     فريبيس
    -0.73
    IsContent
    -0.73
    POSITIVE LOGITS
    !)
    0.75
    !!!)
    0.71
     ENTIRE
    0.66
     (!)
    0.64
    (!)
    0.63
    !!)
    0.62
    !),
    0.61
     ONLY
    0.61
    !).
    0.60
    !
    0.59
    Act Density 0.115%

    No Known Activations