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

    Neuronpedia

    INDEX
    Explanations

    phrases related to error messages or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.16
    åł
    -0.14
    ancellor
    -0.14
    rik
    -0.14
    iman
    -0.14
    andr
    -0.14
    icas
    -0.14
    engu
    -0.14
    itere
    -0.14
    amar
    -0.13
    POSITIVE LOGITS
     volupt
    0.25
     ration
    0.25
     labor
    0.24
     architect
    0.23
     rer
    0.22
     deser
    0.22
     cupid
    0.22
     corrupt
    0.22
     quo
    0.22
     qu
    0.22
    Act Density 0.016%

    No Known Activations