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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey rankings or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìŀij
    -0.17
    .habbo
    -0.15
    ATTLE
    -0.14
     Morrow
    -0.14
     ancest
    -0.14
    ãĥ«ãĥķ
    -0.14
    NSNotificationCenter
    -0.14
    NameValuePair
    -0.14
    curring
    -0.13
    .gallery
    -0.13
    POSITIVE LOGITS
     late
    1.27
    late
    1.07
     Late
    1.03
    Late
    0.96
    æĻļ
    0.54
     tard
    0.45
    lates
    0.42
     позд
    0.39
     lately
    0.38
     tarde
    0.38
    Act Density 0.026%

    No Known Activations