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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and citations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sted
    -0.16
    ouch
    -0.15
    flash
    -0.14
     Deutsch
    -0.14
    ilm
    -0.14
     åĬ
    -0.14
    roker
    -0.14
    0
    -0.14
    _ARGUMENT
    -0.14
    pos
    -0.13
    POSITIVE LOGITS
    HTTPHeader
    0.18
    RuleContext
    0.16
     Altın
    0.15
    mnop
    0.15
    efa
    0.15
    alian
    0.15
    ginas
    0.14
    ahrain
    0.14
    LEAN
    0.14
    hq
    0.14
    Act Density 0.043%

    No Known Activations