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

    Neuronpedia

    INDEX
    Explanations

    words related to intensity or extremity

    oai_token-act-pair · gpt-3.5-turbo

    references to extreme conditions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athan
    -0.85
    din
    -0.76
    ppo
    -0.69
    ilage
    -0.68
    beans
    -0.67
    iak
    -0.67
    ilus
    -0.66
    wan
    -0.66
    know
    -0.66
    sburgh
    -0.66
    POSITIVE LOGITS
     vetting
    1.05
     poverty
    0.95
     lengths
    0.89
     temperatures
    0.89
     amounts
    0.84
     cases
    0.83
     measures
    0.83
     rarity
    0.82
     caution
    0.82
     situations
    0.81
    Act Density 0.048%

    No Known Activations