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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences describing significant aspects or points

    oai_token-act-pair · gpt-3.5-turbo

    phrases that repeatedly mention the word "thing" as a focal point of discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.76
    alone
    -0.75
    oÄŁ
    -0.74
    ierrez
    -0.71
    éĹĺ
    -0.67
    urry
    -0.67
    arak
    -0.66
    endars
    -0.66
    ICO
    -0.65
    SPA
    -0.64
    POSITIVE LOGITS
    iverse
    0.93
     Valiant
    0.84
    osphere
    0.72
    ious
    0.71
     happened
    0.69
    hest
    0.67
    iest
    0.67
     thing
    0.65
     kicker
    0.62
     Wonders
    0.62
    Act Density 0.048%

    No Known Activations