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

    Neuronpedia

    INDEX
    Explanations

    terms related to file extensions

    oai_token-act-pair · gpt-3.5-turbo

    references to extensions or modifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sharks
    -0.79
     wool
    -0.67
     shark
    -0.67
    Reviewer
    -0.66
     traveller
    -0.64
    iard
    -0.64
     eye
    -0.62
    folk
    -0.61
     faces
    -0.61
     Sawyer
    -0.60
    POSITIVE LOGITS
    ension
    1.64
    racted
    1.61
    raction
    1.60
    ensions
    1.55
    ract
    1.52
    ensive
    1.52
    inction
    1.48
    ended
    1.47
    ortion
    1.44
    inct
    1.42
    Act Density 0.017%

    No Known Activations