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

    Neuronpedia

    INDEX
    Explanations

    references to different states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hey
    -0.21
    thon
    -0.17
    sak
    -0.17
    them
    -0.17
    _states
    -0.17
    sov
    -0.17
    los
    -0.17
    hest
    -0.17
     statements
    -0.16
    nop
    -0.16
    POSITIVE LOGITS
    craft
    0.37
    hood
    0.35
    -of
    0.28
    wide
    0.28
    ful
    0.26
    fully
    0.26
    house
    0.24
     Unidos
    0.24
    holder
    0.23
    manship
    0.23
    Act Density 0.104%

    No Known Activations