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

    Neuronpedia

    INDEX
    Explanations

    words related to potential or possibility

    oai_token-act-pair · gpt-3.5-turbo

    references to potential outcomes or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogie
    -0.85
    ĪĴ
    -0.80
    cipline
    -0.74
    ograph
    -0.74
    creen
    -0.73
    bows
    -0.72
    oak
    -0.71
    OTO
    -0.70
    raph
    -0.69
    gall
    -0.67
    POSITIVE LOGITS
    izons
    0.90
    ibilities
    0.86
     implications
    0.84
     claimant
    0.79
     claimants
    0.79
     future
    0.79
     potential
    0.78
     unintended
    0.77
     usefulness
    0.77
     unbeliev
    0.77
    Act Density 0.027%

    No Known Activations