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

    Neuronpedia

    INDEX
    Explanations

    the use of modal verbs indicating possibility or uncertainty about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edo
    -0.16
    reib
    -0.16
    ed
    -0.15
    iland
    -0.15
    Disney
    -0.15
    inks
    -0.14
    chet
    -0.14
    edla
    -0.14
    allis
    -0.14
    ayers
    -0.14
    POSITIVE LOGITS
    iffin
    0.17
    DBC
    0.16
    λοÏį
    0.16
    ãĥ¼ãĥĨ
    0.15
    ÑĢаÑĤно
    0.14
    ÄĻż
    0.14
    ãģ¾ãģł
    0.14
    ahi
    0.14
     اÙĦزر
    0.14
    mpz
    0.13
    Act Density 0.130%

    No Known Activations