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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "probably" indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    men
    -0.17
     supposedly
    -0.15
    itten
    -0.15
    osit
    -0.14
    rar
    -0.14
    ifact
    -0.14
    rst
    -0.14
    rdf
    -0.14
    eren
    -0.14
    aits
    -0.13
    POSITIVE LOGITS
    Ñīа
    0.15
    zag
    0.15
    ÑĤÑĢо
    0.14
    åģ¥
    0.14
    ture
    0.14
    OutOfRangeException
    0.14
     Rog
    0.14
    ewis
    0.13
    .observable
    0.13
    /security
    0.13
    Act Density 0.037%

    No Known Activations