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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional phrases that imply situations or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ç©
    -0.15
    енно
    -0.15
    éĺ³åŁİ
    -0.15
    _GAP
    -0.15
    ɵ
    -0.14
    ãģĽãģ¦
    -0.14
    /umd
    -0.14
    Blocking
    -0.14
    _blocking
    -0.14
    ynth
    -0.13
    POSITIVE LOGITS
    ãĥĨãĥ«
    0.15
    jid
    0.15
    itt
    0.14
    ITT
    0.14
    uis
    0.14
     Vog
    0.14
    edException
    0.14
     there
    0.14
    aq
    0.13
    EXPECTED
    0.13
    Act Density 0.075%

    No Known Activations