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

    Neuronpedia

    INDEX
    Explanations

    references to downward movement or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.07
    4:0.08
    5:0.06
    6:0.08
    7:0.08
    8:0.07
    9:0.10
    10:0.08
    11:0.09
    Negative Logits
     Kong
    -2.99
     Kron
    -2.75
     Rai
    -2.72
    cko
    -2.64
     floppy
    -2.63
     Goth
    -2.60
    phal
    -2.59
    allo
    -2.56
     Kr
    -2.47
    ursed
    -2.47
    POSITIVE LOGITS
     Cosponsors
    2.79
     SEE
    2.72
    ¨
    2.62
    .","
    2.58
     Environmental
    2.46
    SPONSORED
    2.42
     whistleblower
    2.39
    climate
    2.34
    ————
    2.31
     MORE
    2.27
    Act Density 0.000%

    No Known Activations