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

    Neuronpedia

    INDEX
    Explanations

    programming variables and parameters related to indexing and memory management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     &↵
    -0.14
    '(
    -0.13
     niche
    -0.13
    indow
    -0.13
     Dro
    -0.13
    ái
    -0.13
    obo
    -0.13
    mez
    -0.13
     wa
    -0.13
     Wa
    -0.13
    POSITIVE LOGITS
     +=
    0.43
     -=
    0.35
    +=
    0.33
     *=
    0.30
     /=
    0.24
     +=↵
    0.23
    +=(
    0.23
    -=
    0.23
    *=
    0.22
    +='
    0.22
    Act Density 0.042%

    No Known Activations