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

    Neuronpedia

    INDEX
    Explanations

    terms related to complexity or multi-functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.16
    Audit
    -0.15
    nings
    -0.15
    irsch
    -0.14
     Byron
    -0.14
     Strap
    -0.14
    iT
    -0.13
    missions
    -0.13
    warts
    -0.13
    agnost
    -0.13
    POSITIVE LOGITS
    arious
    0.27
     facet
    0.22
    ocal
    0.20
    unction
    0.20
    .fac
    0.20
    ARIO
    0.19
    _fac
    0.19
     facets
    0.18
    ac
    0.18
     requ
    0.18
    Act Density 0.006%

    No Known Activations