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

    Neuronpedia

    INDEX
    Explanations

    references to scholarly publications and sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Equivalent
    -0.17
    athom
    -0.15
     cade
    -0.15
     equivalent
    -0.14
    abis
    -0.14
    åħĥ
    -0.14
    enton
    -0.14
    stell
    -0.14
     lect
    -0.14
    reamble
    -0.14
    POSITIVE LOGITS
    ories
    0.26
    orie
    0.26
     Role
    0.20
    ologie
    0.20
    or
    0.19
     Rise
    0.19
    orias
    0.19
     Roles
    0.18
    oretical
    0.18
     role
    0.18
    Act Density 0.115%

    No Known Activations