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

    Neuronpedia

    INDEX
    Explanations

    words related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    references to turning points or pivotal moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    accompan
    -0.88
    cffff
    -0.63
    enegger
    -0.62
     ubiqu
    -0.58
    rising
    -0.57
     ceilings
    -0.57
    pelling
    -0.57
    cham
    -0.56
    ccoli
    -0.56
     newsletters
    -0.55
    POSITIVE LOGITS
     tide
    0.99
     knob
    0.81
    Ī
    0.79
     Into
    0.77
    Ń·
    0.76
     tides
    0.76
     INTO
    0.75
    ¦
    0.72
    ¿
    0.71
     fortunes
    0.71
    Act Density 0.096%

    No Known Activations