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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the ability to perform an action or see something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    455
    -0.15
    usted
    -0.15
    abaj
    -0.15
    kowski
    -0.15
    erten
    -0.14
    ultiply
    -0.14
    ego
    -0.14
    åĸ
    -0.14
    uct
    -0.14
    689
    -0.14
    POSITIVE LOGITS
    ед
    0.15
    ÙĩÙĨ
    0.15
    Äįen
    0.15
     kop
    0.14
    ÄĽÅĻ
    0.14
    .Reporting
    0.14
     Ro
    0.14
    seed
    0.14
    uba
    0.14
    orst
    0.14
    Act Density 0.023%

    No Known Activations