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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to resolving situations or reaching conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.75
    cious
    -0.73
    asus
    -0.72
    uart
    -0.68
     tyr
    -0.67
    erva
    -0.64
    pty
    -0.63
    encrypted
    -0.62
    Pers
    -0.62
    aign
    -0.61
    POSITIVE LOGITS
    fitting
    0.73
    fitted
    0.72
    icago
    0.66
    flow
    0.65
     trillions
    0.65
     agreements
    0.64
     how
    0.62
    uate
    0.62
    framework
    0.61
    posts
    0.61
    Act Density 0.020%

    No Known Activations