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

    Neuronpedia

    INDEX
    Explanations

    references to updates or changes in software functionalities or compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordo
    -0.18
    tmpl
    -0.16
    elenium
    -0.15
    uptools
    -0.15
    valuator
    -0.15
    illon
    -0.14
    ras
    -0.14
    ç·ł
    -0.14
    _locs
    -0.14
    ascar
    -0.13
    POSITIVE LOGITS
     compatibility
    0.43
     Compatibility
    0.37
     backward
    0.36
     compat
    0.36
     compatible
    0.34
     backwards
    0.33
    compat
    0.33
     incompatible
    0.31
    Compatibility
    0.31
     support
    0.30
    Act Density 0.075%

    No Known Activations