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

    Neuronpedia

    INDEX
    Explanations

    coordinating conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.10
    3:0.13
    4:0.05
    5:0.02
    6:0.06
    7:0.28
    8:0.04
    9:0.04
    10:0.08
    11:0.11
    Negative Logits
     ditch
    -1.47
    andowski
    -1.46
     whistle
    -1.44
     descent
    -1.43
    iewicz
    -1.40
     advice
    -1.40
     tips
    -1.39
     weave
    -1.35
     rave
    -1.35
    rists
    -1.34
    POSITIVE LOGITS
     XXX
    1.69
     AUTH
    1.66
    XXX
    1.56
    mun
    1.48
    Reply
    1.46
     boutique
    1.43
     CVE
    1.42
     XL
    1.41
    afort
    1.39
    content
    1.37
    Act Density 0.000%

    No Known Activations