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

    Neuronpedia

    INDEX
    Explanations

    phrases predicting future outcomes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.22
    3:0.04
    4:0.05
    5:0.02
    6:0.26
    7:0.20
    8:0.02
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    erity
    -1.52
    Vers
    -1.48
    president
    -1.37
    Bet
    -1.36
     Pax
    -1.36
    fml
    -1.34
    ipolar
    -1.33
    acia
    -1.32
    ocity
    -1.32
    ghazi
    -1.31
    POSITIVE LOGITS
    mma
    1.68
    lishes
    1.53
     Tatt
    1.48
    rated
    1.40
     Mean
    1.35
     Venezuel
    1.34
    define
    1.34
    clips
    1.34
    metic
    1.27
     Eternity
    1.27
    Act Density 0.002%

    No Known Activations