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

    Neuronpedia

    INDEX
    Explanations

    references to specific graduation classes and reunions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roller
    -0.18
     Roller
    -0.17
    inen
    -0.17
    DNA
    -0.16
    rollers
    -0.16
    ILA
    -0.15
    rollo
    -0.15
    igy
    -0.15
    RTL
    -0.15
    ÏĦÏģο
    -0.14
    POSITIVE LOGITS
    fov
    0.15
    ůj
    0.15
     aras
    0.14
    airs
    0.14
    ourced
    0.14
    aroo
    0.14
    _nl
    0.14
     lagi
    0.14
     intermediary
    0.14
    /Branch
    0.13
    Act Density 0.022%

    No Known Activations