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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or increasing intensity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongo
    -0.15
    ordin
    -0.15
    pit
    -0.15
    816
    -0.15
    ä¿Ĥ
    -0.14
    elt
    -0.14
     Richards
    -0.14
    ehir
    -0.13
    _initializer
    -0.13
    йн
    -0.13
    POSITIVE LOGITS
     increasingly
    0.18
    ubo
    0.16
    cci
    0.15
    è¶Ĭ
    0.15
    ä¸ģ
    0.15
    _until
    0.14
    é«
    0.14
     Bd
    0.14
    UBL
    0.14
    pai
    0.14
    Act Density 0.193%

    No Known Activations