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

    Neuronpedia

    INDEX
    Explanations

    examples of words or phrases indicating a negative or unfortunate situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.06
    3:0.27
    4:0.02
    5:0.02
    6:0.09
    7:0.05
    8:0.05
    9:0.12
    10:0.11
    11:0.10
    Negative Logits
    ASC
    -1.15
    intensive
    -1.05
    ifted
    -1.03
    ASED
    -1.03
    risis
    -1.03
    ISON
    -1.02
    adr
    -1.01
    ylene
    -0.99
    ="/
    -0.99
    iop
    -0.99
    POSITIVE LOGITS
    glers
    1.12
     IDs
    1.11
    bite
    1.01
     craw
    1.00
     smokes
    0.96
    azines
    0.95
     PIN
    0.95
     headlines
    0.95
    bats
    0.93
     Staten
    0.92
    Act Density 0.006%

    No Known Activations