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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rael
    -0.14
     can
    -0.13
    073
    -0.13
    ãĤ¤ãĥ³ãĥĪ
    -0.13
    å®ĭä½ĵ
    -0.13
    curacy
    -0.13
    ds
    -0.12
    ={`${
    -0.12
    esi
    -0.12
    ANJI
    -0.12
    POSITIVE LOGITS
    -bodied
    0.21
    NullException
    0.17
    tings
    0.17
    berra
    0.17
    /disable
    0.17
    asty
    0.16
    ipar
    0.15
    sert
    0.15
    cerr
    0.15
    ister
    0.15
    Act Density 0.038%

    No Known Activations