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

    Neuronpedia

    INDEX
    Explanations

    structured references and citations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elden
    -0.19
    eldon
    -0.16
    _TRA
    -0.15
     pii
    -0.15
    ÄŁa
    -0.14
    DSA
    -0.13
    llen
    -0.13
     Blank
    -0.13
    ection
    -0.13
    eling
    -0.13
    POSITIVE LOGITS
     SYN
    0.18
     Hence
    0.16
    USAGE
    0.16
     hence
    0.16
     Syn
    0.16
    Usage
    0.16
    usage
    0.15
    apo
    0.15
    Syn
    0.15
     Usage
    0.15
    Act Density 0.005%

    No Known Activations