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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and first-person perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.76
     neighborhood
    -0.56
     câncer
    -0.56
    存于互联网档案馆
    -0.55
     neighborhoods
    -0.55
     pinulongan
    -0.54
     agregado
    -0.54
     Agrega
    -0.52
     agrega
    -0.52
     aluminum
    -0.52
    POSITIVE LOGITS
     Whilst
    0.99
    Whilst
    0.98
     whilst
    0.94
    initialise
    0.89
     reck
    0.81
    cognised
    0.81
     realise
    0.79
     tyres
    0.79
     tyre
    0.78
     envisage
    0.78
    Act Density 0.203%

    No Known Activations