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

    Neuronpedia

    INDEX
    Explanations

    numerical values or references throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.10
    3:0.05
    4:0.05
    5:0.04
    6:0.18
    7:0.19
    8:0.04
    9:0.04
    10:0.14
    11:0.08
    Negative Logits
     anat
    -1.46
     trademarks
    -1.45
     apost
    -1.41
     hackers
    -1.39
    ustainable
    -1.39
     fax
    -1.37
     clutch
    -1.37
     gel
    -1.36
     welcome
    -1.34
     holster
    -1.34
    POSITIVE LOGITS
     Balanced
    1.63
     Discovery
    1.49
     totality
    1.47
    ngth
    1.42
    abba
    1.40
     Layout
    1.38
    specified
    1.37
    aukee
    1.37
     Survivor
    1.37
     Conditions
    1.36
    Act Density 0.021%

    No Known Activations