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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating value or worthiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otti
    -0.17
    istrate
    -0.16
    verting
    -0.16
    zure
    -0.15
    porto
    -0.15
    ccess
    -0.15
    बर
    -0.14
    izada
    -0.14
    iens
    -0.14
    erate
    -0.14
    POSITIVE LOGITS
    ful
    0.23
    iness
    0.23
    fully
    0.20
    FUL
    0.17
    ies
    0.16
    iest
    0.16
    lessly
    0.16
    itt
    0.15
    fulness
    0.15
    ries
    0.15
    Act Density 0.029%

    No Known Activations