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

    Neuronpedia

    INDEX
    Explanations

    quotes and attributions from various speakers or authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.65
     تانيه
    -0.65
     yourselves
    -0.65
    OGND
    -0.62
     themselves
    -0.60
     لينك
    -0.59
     tutte
    -0.59
     venons
    -0.57
     oublié
    -0.57
     Itself
    -0.56
    POSITIVE LOGITS
     said
    0.91
     spokeswoman
    0.82
     spokesman
    0.78
     spokesperson
    0.76
     says
    0.72
     explains
    0.71
    })`
    0.70
     explained
    0.70
    said
    0.67
    says
    0.64
    Act Density 0.174%

    No Known Activations