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

    Neuronpedia

    INDEX
    Explanations

    specific passive constructions and formal language indicating procedural or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atial
    -0.15
     Dawn
    -0.15
    PPER
    -0.14
    antro
    -0.14
    emouth
    -0.14
    MOTE
    -0.14
    azÄĥ
    -0.14
    ç«ĭãģ¦
    -0.13
    iseum
    -0.13
    inely
    -0.13
    POSITIVE LOGITS
    cken
    0.17
    itsu
    0.15
    zug
    0.14
    623
    0.13
    ambre
    0.13
    vik
    0.13
    æĵ
    0.12
    à¥ģà¤Ī
    0.12
    ucken
    0.12
    luck
    0.12
    Act Density 0.243%

    No Known Activations