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

    Neuronpedia

    INDEX
    Explanations

    expressions of apology, gratitude, and love

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogne
    -0.14
    IfNeeded
    -0.14
    _capability
    -0.14
    loo
    -0.14
    ofilm
    -0.13
    ishi
    -0.13
     Evel
    -0.13
    anco
    -0.13
    ÅĻet
    -0.13
    Boom
    -0.13
    POSITIVE LOGITS
    enna
    0.15
    engo
    0.15
     Exc
    0.15
    Ỽ
    0.14
    kaar
    0.13
    kk
    0.13
     bona
    0.13
     InitializeComponent
    0.13
    chg
    0.13
     Cup
    0.13
    Act Density 0.107%

    No Known Activations