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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "fully."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aggress
    -0.15
    ole
    -0.15
    olit
    -0.14
    asan
    -0.14
     intim
    -0.14
    lement
    -0.14
     meg
    -0.14
    WARD
    -0.14
    -large
    -0.13
    .defaults
    -0.13
    POSITIVE LOGITS
     fully
    0.23
     fled
    0.22
    Fully
    0.20
     Fully
    0.19
     flesh
    0.18
    QualifiedName
    0.18
    -loaded
    0.17
    -functional
    0.16
     loaded
    0.16
    loaded
    0.16
    Act Density 0.022%

    No Known Activations