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

    Neuronpedia

    INDEX
    Explanations

    repetitive word usage, particularly emphasizing the word "also."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĭãĤ¢
    -0.17
    istik
    -0.17
    oller
    -0.15
    isty
    -0.15
    .Aggressive
    -0.14
     neboť
    -0.14
    ller
    -0.14
    roe
    -0.13
    inta
    -0.13
    liable
    -0.13
    POSITIVE LOGITS
    _perm
    0.17
    porte
    0.16
    inic
    0.15
    otti
    0.14
    cht
    0.14
     SVC
    0.14
    born
    0.14
    perm
    0.14
    ysz
    0.14
    ima
    0.13
    Act Density 0.059%

    No Known Activations