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

    Neuronpedia

    INDEX
    Explanations

    timestamps or dates in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.14
    3:0.14
    4:0.09
    5:0.03
    6:0.06
    7:0.05
    8:0.05
    9:0.05
    10:0.15
    11:0.12
    Negative Logits
    anski
    -1.43
     envy
    -1.38
     chase
    -1.35
    plot
    -1.30
     racer
    -1.30
    thood
    -1.29
    Pg
    -1.28
    puted
    -1.28
     minus
    -1.27
     cruising
    -1.25
    POSITIVE LOGITS
    �
    1.23
    iatus
    1.20
     Elk
    1.20
     TAMADRA
    1.19
    �士
    1.18
    podcast
    1.18
     Cable
    1.17
     mac
    1.17
     Bastard
    1.16
     Conan
    1.16
    Act Density 0.002%

    No Known Activations