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

    Neuronpedia

    INDEX
    Explanations

    references to personal achievements and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PBS
    -0.16
    awe
    -0.15
    baar
    -0.14
    -ÐŁÐµÑĤеÑĢб
    -0.14
    anst
    -0.14
    .FC
    -0.14
    iais
    -0.14
    wart
    -0.13
     pand
    -0.13
    unate
    -0.13
    POSITIVE LOGITS
     OMIT
    0.15
    hausen
    0.15
    engin
    0.15
    iyas
    0.15
    ús
    0.15
    566
    0.15
    iets
    0.14
    ól
    0.14
    [Test
    0.14
    MethodInfo
    0.14
    Act Density 0.036%

    No Known Activations