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

    Neuronpedia

    INDEX
    Explanations

    instances of quietly or silently performed actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ekonomi
    -0.54
    ợp
    -0.54
     Einrichtung
    -0.54
     espar
    -0.53
    aughey
    -0.53
     parrots
    -0.52
    ApiProperty
    -0.52
     spes
    -0.51
     Interpre
    -0.50
    üme
    -0.49
    POSITIVE LOGITS
     hidden
    1.10
     invisible
    1.06
     secret
    1.06
     secretly
    1.05
     invis
    0.96
    invisible
    0.94
     Invisible
    0.89
    secret
    0.88
    Invisible
    0.88
     behind
    0.87
    Act Density 0.326%

    No Known Activations