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

    Neuronpedia

    INDEX
    Explanations

    specific keywords related to initial statements or introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bonitas
    -0.57
     danni
    -0.52
     kehadiran
    -0.51
     Pob
    -0.50
    ioutil
    -0.49
    Presence
    -0.48
     présence
    -0.47
     pioggia
    -0.47
    Pob
    -0.47
     Jehová
    -0.46
    POSITIVE LOGITS
    findpost
    1.21
    PerformLayout
    0.84
     autorytatywna
    0.82
    +#+#
    0.77
    AddTagHelper
    0.77
    DeleteBehavior
    0.75
    tagHelperRunner
    0.75
    RectangleBorder
    0.75
    _));
    0.72
    MessageState
    0.72
    Act Density 0.394%

    No Known Activations