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

    Neuronpedia

    INDEX
    Explanations

    abstract symbols and special characters, possibly indicating a focus on encoding or formatting elements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ead
    -0.16
    inal
    -0.15
    .hs
    -0.15
    oplay
    -0.15
    annis
    -0.15
    arie
    -0.14
    onis
    -0.14
    chop
    -0.14
    rete
    -0.14
    agn
    -0.14
    POSITIVE LOGITS
     marshaller
    0.15
     ENG
    0.15
    Scalars
    0.15
     US
    0.14
    ENG
    0.14
     eng
    0.14
    EventType
    0.13
    豪
    0.13
     jadx
    0.13
    _US
    0.13
    Act Density 0.113%

    No Known Activations