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

    Neuronpedia

    INDEX
    Explanations

    guidelines and rules related to prohibited activities and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è³¢
    -0.16
     немного
    -0.15
     Various
    -0.15
     appropriate
    -0.14
     ëĭ¤ìĸij
    -0.14
    aira
    -0.14
     Inherits
    -0.14
     discreet
    -0.14
    _kv
    -0.14
    aptop
    -0.13
    POSITIVE LOGITS
     unless
    0.35
     anything
    0.33
     any
    0.30
     ANY
    0.30
     nor
    0.30
    unless
    0.30
    anything
    0.30
    ä»»ä½ķ
    0.29
     anymore
    0.26
    Unless
    0.26
    Act Density 0.328%

    No Known Activations