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

    Neuronpedia

    INDEX
    Explanations

    markers related to time and structure within written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulus
    -0.15
    obao
    -0.14
    yal
    -0.14
    okol
    -0.14
    ovi
    -0.14
    amient
    -0.14
    .motion
    -0.14
    bell
    -0.14
    tright
    -0.14
    encil
    -0.14
    POSITIVE LOGITS
    ODO
    0.16
    ãģĭãģĦ
    0.15
     Gall
    0.15
    ëłµ
    0.15
     confidence
    0.14
    ropol
    0.14
    گاÙĨ
    0.14
    enes
    0.13
     advantage
    0.13
    odo
    0.13
    Act Density 0.001%

    No Known Activations