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

    Neuronpedia

    INDEX
    Explanations

    superlatives indicating extremes or best qualities

    oai_token-act-pair · gpt-3.5-turbo

    hyperbolic expressions of the word "ever."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.79
     Beir
    -0.77
    resy
    -0.74
    itu
    -0.74
    insk
    -0.72
    oren
    -0.72
    oult
    -0.70
    arity
    -0.70
    oad
    -0.69
    eness
    -0.69
    POSITIVE LOGITS
     recorded
    0.97
     dreamed
    0.91
     conceived
    0.90
     seen
    0.88
     imagined
    0.88
     assembled
    0.86
     achieved
    0.85
     heard
    0.84
     existed
    0.84
     produced
    0.84
    Act Density 0.016%

    No Known Activations