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

    Neuronpedia

    INDEX
    Explanations

    numeric values and percentages related to data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onOptions
    -0.51
     Satt
    -0.47
    SetOutput
    -0.46
     Lubbock
    -0.40
     Lapp
    -0.40
     suc
    -0.39
     Epp
    -0.38
    smooth
    -0.37
     sm
    -0.37
    toc
    -0.37
    POSITIVE LOGITS
     ainfi
    0.71
     mauva
    0.67
     plufieurs
    0.64
     feroit
    0.63
     húmedo
    0.60
     cartera
    0.60
    setVerticalGroup
    0.60
     hâte
    0.59
     ferrovia
    0.59
     recrutement
    0.59
    Act Density 0.415%

    No Known Activations