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

    Neuronpedia

    INDEX
    Explanations

    presence of verbs indicating existence or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſche
    -0.99
     pleaſure
    -0.94
     houſe
    -0.92
     Efq
    -0.91
     fubject
    -0.91
     purpoſe
    -0.90
     itſelf
    -0.89
     Jefus
    -0.89
     juſ
    -0.89
     Monfieur
    -0.87
    POSITIVE LOGITS
    UpInside
    0.81
     not
    0.74
     a
    0.67
     are
    0.59
     in
    0.58
     at
    0.57
     being
    0.55
    endphp
    0.52
    ’
    0.52
     also
    0.52
    Act Density 0.381%

    No Known Activations