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

    Neuronpedia

    INDEX
    Explanations

    prepositions and time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.08
    3:0.07
    4:0.19
    5:0.05
    6:0.03
    7:0.23
    8:0.04
    9:0.04
    10:0.13
    11:0.06
    Negative Logits
     successes
    -1.56
    funding
    -1.38
    gettable
    -1.37
    覚醒
    -1.36
     crowdfunding
    -1.36
     sails
    -1.36
     referrals
    -1.35
     campaigns
    -1.34
    advertising
    -1.33
    poons
    -1.33
    POSITIVE LOGITS
    Correct
    1.56
     Lange
    1.43
     Bellev
    1.38
    onday
    1.37
     2100
    1.36
     Qiao
    1.35
    Fri
    1.34
     Correctional
    1.33
     Wednesday
    1.33
     Division
    1.31
    Act Density 0.001%

    No Known Activations