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

    Neuronpedia

    INDEX
    Explanations

    emphatic expressions of totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     phosphory
    -0.56
     marquées
    -0.55
     PopupWindow
    -0.55
     heur
    -0.54
    imath
    -0.54
    ijão
    -0.52
     IAA
    -0.52
    gridx
    -0.51
    chkin
    -0.51
    有料
    -0.51
    POSITIVE LOGITS
     completely
    3.86
     entirely
    3.78
     totally
    3.48
     Completely
    3.42
    completely
    3.27
    Completely
    3.20
     wholly
    2.93
     Totally
    2.90
    totally
    2.87
     completamente
    2.77
    Act Density 0.146%

    No Known Activations