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

    Neuronpedia

    INDEX
    Explanations

    web links and references

    oai_token-act-pair · gpt-3.5-turbo

    web-related content and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.62
     ®
    -0.62
     IST
    -0.61
     «
    -0.58
     Murdoch
    -0.57
     abiding
    -0.56
     Sao
    -0.55
     Cald
    -0.55
     bonding
    -0.54
     McMaster
    -0.54
    POSITIVE LOGITS
    /,
    1.15
    /)
    1.12
    /_
    1.05
    /?
    1.05
    /
    0.99
    /-
    0.97
    /.
    0.95
    /#
    0.91
    php
    0.91
    /"
    0.84
    Act Density 0.056%

    No Known Activations