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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "like" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frey
    -0.17
    Å¡lo
    -0.16
    ãĤ¤ãĤº
    -0.15
     banking
    -0.14
    ÑĪÑĤ
    -0.14
     Wallace
    -0.14
    Iron
    -0.14
    chia
    -0.13
    yles
    -0.13
    WebRequest
    -0.13
    POSITIVE LOGITS
    ewise
    0.27
    elihood
    0.25
    wise
    0.23
    ewis
    0.21
    ening
    0.20
    WISE
    0.20
    ens
    0.19
    eli
    0.19
    ened
    0.18
    kle
    0.18
    Act Density 0.010%

    No Known Activations