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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "top" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĥÏĩ
    -0.15
    ileo
    -0.14
    tsky
    -0.14
    yster
    -0.14
    ena
    -0.13
    ivant
    -0.13
     Siz
    -0.13
    553
    -0.13
    embre
    -0.13
     æķ
    -0.13
    POSITIVE LOGITS
    ikler
    0.17
    ãĥ¼ãĥį
    0.16
    ãĥ¬ãĥ¼
    0.16
     ten
    0.15
     few
    0.15
    ernal
    0.15
    _ten
    0.15
    ायल
    0.15
     spot
    0.14
    ÅĤe
    0.14
    Act Density 0.020%

    No Known Activations