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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "state" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _states
    -0.21
    hey
    -0.21
    Statement
    -0.19
    sov
    -0.18
     statements
    -0.18
    _statement
    -0.18
     Statement
    -0.18
    them
    -0.17
     Statements
    -0.17
    sak
    -0.17
    POSITIVE LOGITS
    craft
    0.34
    hood
    0.31
    ful
    0.24
    -of
    0.23
    fully
    0.22
     Unidos
    0.21
    /local
    0.21
    house
    0.21
    coach
    0.20
    MENTS
    0.19
    Act Density 0.085%

    No Known Activations