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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the topic of discussion or focus in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /she
    -0.15
    _ASSUME
    -0.14
    \CMS
    -0.13
    InputBorder
    -0.13
    _detalle
    -0.13
    /her
    -0.13
    StringEncoding
    -0.13
    QUENCY
    -0.13
    Č
    -0.13
    _IOC
    -0.13
    POSITIVE LOGITS
    /about
    0.22
     the
    0.20
    /by
    0.20
    wards
    0.19
    ness
    0.18
    neath
    0.18
    st
    0.18
    -
    0.17
    /out
    0.17
    lain
    0.16
    Act Density 0.362%

    No Known Activations