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

    Neuronpedia

    INDEX
    Explanations

    actions related to collaboration and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.09
    3:0.33
    4:0.12
    5:0.02
    6:0.02
    7:0.09
    8:0.03
    9:0.04
    10:0.08
    11:0.09
    Negative Logits
    exempt
    -1.53
    Origin
    -1.45
    Insert
    -1.42
     Internal
    -1.37
     <-
    -1.36
    objects
    -1.34
     Entered
    -1.33
    uphem
    -1.33
    Account
    -1.33
    エル
    -1.31
    POSITIVE LOGITS
     tomorrow
    1.99
     someday
    1.85
    morrow
    1.79
    .","
    1.74
    ️
    1.70
    izons
    1.63
     hopefully
    1.62
     responsibly
    1.60
    anooga
    1.57
     goodbye
    1.56
    Act Density 0.032%

    No Known Activations