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

    Neuronpedia

    INDEX
    Explanations

    references to rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omes
    -0.17
    esser
    -0.16
    razione
    -0.16
    rog
    -0.16
    IDES
    -0.15
    allon
    -0.15
    apo
    -0.15
    phy
    -0.14
    rees
    -0.14
    ESS
    -0.14
    POSITIVE LOGITS
    ì¹Ļ
    0.17
    .scalablytyped
    0.15
     adm
    0.15
    enstein
    0.14
    indrome
    0.14
    inalg
    0.14
    esktop
    0.14
    ambi
    0.14
    atican
    0.13
    instein
    0.13
    Act Density 0.041%

    No Known Activations