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

    Neuronpedia

    INDEX
    Explanations

    hashtags or marker symbols typically used in formatting or categorizing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ->
    -0.14
    "
    -0.14
    dyby
    -0.13
     seedu
    -0.13
     volum
    -0.13
    erialized
    -0.13
    >{!!
    -0.13
    erus
    -0.13
    abi
    -0.13
    úb
    -0.13
    POSITIVE LOGITS
     Seznam
    0.17
    RIES
    0.16
    olley
    0.16
    ako
    0.16
    encoding
    0.15
    ERG
    0.15
     Lista
    0.15
     seznam
    0.14
    errupt
    0.14
    okit
    0.14
    Act Density 0.008%

    No Known Activations