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

    Neuronpedia

    INDEX
    Explanations

    words related to anticipation or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.05
    2:0.07
    3:0.21
    4:0.13
    5:0.04
    6:0.14
    7:0.04
    8:0.07
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    nesday
    -1.60
     autos
    -1.51
    ◼
    -1.50
    ModLoader
    -1.43
    agonist
    -1.37
    orically
    -1.34
    inarily
    -1.33
     resid
    -1.32
     inevitably
    -1.32
     unavoid
    -1.31
    POSITIVE LOGITS
     Veget
    1.37
    mite
    1.34
    Joined
    1.32
     Died
    1.30
     Melania
    1.27
     guiName
    1.24
    thia
    1.18
     flowers
    1.17
     Gets
    1.17
     Theresa
    1.16
    Act Density 0.001%

    No Known Activations