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

    Neuronpedia

    INDEX
    Explanations

    references to traceability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĢ
    -0.17
    qm
    -0.16
    615
    -0.16
    ÙĦÙĬÙħ
    -0.15
    imd
    -0.14
    -widgets
    -0.14
    rians
    -0.14
    readcr
    -0.14
    ocre
    -0.14
    iw
    -0.14
    POSITIVE LOGITS
    ability
    0.34
    .Trace
    0.30
    able
    0.28
    (trace
    0.25
    .trace
    0.24
    backs
    0.24
     Trace
    0.23
    ABILITY
    0.23
    y
    0.23
     trace
    0.22
    Act Density 0.012%

    No Known Activations