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

    Neuronpedia

    INDEX
    Explanations

    terms related to associations or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.18
    اÙĩ
    -0.15
     Priv
    -0.14
    lobs
    -0.14
    ahn
    -0.14
    rust
    -0.14
    506
    -0.14
    Ł
    -0.14
    Priv
    -0.13
    ulan
    -0.13
    POSITIVE LOGITS
    dale
    0.17
    æ³Ĭ
    0.16
    SOLE
    0.14
    facts
    0.14
    gor
    0.14
    /loader
    0.14
    dos
    0.14
    avig
    0.14
     homo
    0.14
     with
    0.13
    Act Density 0.023%

    No Known Activations