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

    Neuronpedia

    INDEX
    Explanations

    positive and negative sentiment indicators in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.96
    -0.91
     оригіналу
    -0.90
     Walkover
    -0.89
     cire
    -0.87
     Malk
    -0.87
    InjectAttribute
    -0.85
     Monfieur
    -0.83
    crumb
    -0.83
     Cire
    -0.82
    POSITIVE LOGITS
     Pos
    2.19
    pos
    2.18
     pos
    2.17
    Pos
    2.03
     POS
    1.83
    POS
    1.79
     POSS
    1.27
     poses
    1.24
    getPos
    1.24
    Poss
    1.21
    Act Density 0.075%

    No Known Activations