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

    Neuronpedia

    INDEX
    Explanations

    mathematical properties and distributions related to functions and their analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è£ķ
    -0.16
     Goodman
    -0.15
     Choice
    -0.14
     ----------------------------------------------------------------------------↵
    -0.14
    олом
    -0.13
    /Branch
    -0.13
    _spell
    -0.13
    ahlen
    -0.13
     zaz
    -0.13
    ern
    -0.13
    POSITIVE LOGITS
     fixed
    0.22
     size
    0.19
     exactly
    0.19
     constant
    0.18
     prescribed
    0.18
    .fixed
    0.17
    fixed
    0.16
     type
    0.16
     order
    0.16
     rank
    0.16
    Act Density 0.141%

    No Known Activations