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

    Neuronpedia

    INDEX
    Explanations

    the word "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.03
    2:0.02
    3:0.05
    4:0.04
    5:0.14
    6:0.04
    7:0.14
    8:0.12
    9:0.16
    10:0.01
    11:0.03
    Negative Logits
     bullish
    -2.12
     pessimistic
    -1.88
     optimistic
    -1.77
     Hun
    -1.76
     hype
    -1.75
    achev
    -1.74
    kish
    -1.72
     Angry
    -1.72
     Fool
    -1.71
     Incre
    -1.70
    POSITIVE LOGITS
     restrooms
    2.36
    property
    2.25
    sale
    2.19
    ommod
    2.16
     rentals
    2.12
    CLUD
    2.10
     bathrooms
    2.01
    elfare
    2.00
     restroom
    1.94
     rental
    1.94
    Act Density 0.000%

    No Known Activations