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

    Neuronpedia

    INDEX
    Explanations

    references to specific entries in a structured format, likely related to data or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIORITY
    -0.18
    intl
    -0.16
     же
    -0.15
    iferay
    -0.15
    ipment
    -0.15
    iki
    -0.15
    REFERRED
    -0.15
    ियत
    -0.15
    ongan
    -0.15
    ching
    -0.14
    POSITIVE LOGITS
    prising
    0.22
    alus
    0.21
    backs
    0.16
    bull
    0.16
    prises
    0.16
    ebe
    0.15
    olicit
    0.15
    holm
    0.15
    ting
    0.15
    133
    0.15
    Act Density 0.028%

    No Known Activations