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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .backup
    -0.15
    .StoredProcedure
    -0.15
    aron
    -0.15
    asca
    -0.15
    ulo
    -0.15
    SPACE
    -0.14
    emente
    -0.14
    apiro
    -0.14
    eron
    -0.14
    ULO
    -0.14
    POSITIVE LOGITS
    xies
    0.16
     caught
    0.15
    ecies
    0.14
     heading
    0.14
    Catch
    0.14
    czy
    0.14
     paralle
    0.14
     Ðĵол
    0.13
     catch
    0.13
     everyone
    0.13
    Act Density 0.049%

    No Known Activations