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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "by" and also references to publications or papers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    denk
    -0.59
     endregion
    -0.54
    PerformLayout
    -0.54
    ρχ
    -0.53
     Moura
    -0.51
    Intervention
    -0.50
     accountability
    -0.49
    veillance
    -0.49
    ành
    -0.48
    Breite
    -0.48
    POSITIVE LOGITS
     SIZE
    0.93
    tagHelperRunner
    0.84
    ="-
    0.84
    SIZE
    0.81
     الحره
    0.75
     size
    0.71
     Size
    0.70
     يتيمه
    0.69
     defaultstate
    0.69
     المعيارى
    0.65
    Act Density 0.000%

    No Known Activations