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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to specific historical and cultural entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.90
     Kenner
    -0.88
     Mase
    -0.85
     Gaston
    -0.82
     Schwarzenegger
    -0.77
    Kop
    -0.76
     Darn
    -0.76
     Heads
    -0.75
     GLS
    -0.74
     Jansen
    -0.73
    POSITIVE LOGITS
    ณฑ
    0.77
    Schedulers
    0.71
    arakhand
    0.69
    ipelago
    0.68
    vician
    0.67
    zzá
    0.67
    ervlak
    0.67
     colspan
    0.66
     Maruti
    0.66
     Gru
    0.66
    Act Density 2.924%

    No Known Activations