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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation of effectiveness or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     typeid
    -0.15
    tsky
    -0.15
    ugo
    -0.15
    Ð®ÐĽ
    -0.14
    ego
    -0.14
    loth
    -0.14
    aname
    -0.14
    ston
    -0.14
    ugu
    -0.14
    CharacterSet
    -0.14
    POSITIVE LOGITS
     much
    0.17
     than
    0.16
     surprises
    0.15
    much
    0.15
    textTheme
    0.14
     actually
    0.14
    conn
    0.14
    qi
    0.14
    ладÑĥ
    0.14
    praak
    0.14
    Act Density 0.082%

    No Known Activations