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

    Neuronpedia

    INDEX
    Explanations

    phrases related to options and agreement conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.06
    2:0.09
    3:0.06
    4:0.03
    5:0.16
    6:0.06
    7:0.10
    8:0.07
    9:0.15
    10:0.07
    11:0.09
    Negative Logits
    \":
    -1.71
    matter
    -1.48
     Myst
    -1.45
    gow
    -1.40
     resil
    -1.36
    abal
    -1.35
     Franch
    -1.34
    icion
    -1.34
    boys
    -1.33
    gru
    -1.32
    POSITIVE LOGITS
     unsub
    1.52
     URL
    1.50
     captcha
    1.50
     intrusive
    1.47
     Sponsor
    1.41
     html
    1.40
     tolerated
    1.40
     embed
    1.39
    iphate
    1.38
    �
    1.35
    Act Density 0.004%

    No Known Activations