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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses related to decision-making or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    čiau
    -0.53
     couvrir
    -0.52
     conduct
    -0.51
    ҥ
    -0.50
    itian
    -0.49
     发表于
    -0.49
     Jennings
    -0.47
    ợn
    -0.47
     szint
    -0.46
     peines
    -0.46
    POSITIVE LOGITS
     kasarigan
    0.75
     oprot
    0.72
    AddTagHelper
    0.72
     Roskov
    0.69
    bootstrapcdn
    0.69
    zbęd
    0.68
     للمعارف
    0.68
     المعيارى
    0.67
     correctes
    0.67
     summers
    0.66
    Act Density 0.305%

    No Known Activations