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

    Neuronpedia

    INDEX
    Explanations

    references to organizational missions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elier
    -0.15
    porter
    -0.15
     Shelf
    -0.15
    ude
    -0.15
    ventions
    -0.14
    136
    -0.14
    558
    -0.14
    ilde
    -0.14
    action
    -0.14
     religion
    -0.14
    POSITIVE LOGITS
     statement
    0.33
     Statement
    0.29
    aries
    0.29
     statements
    0.29
    ary
    0.28
    statement
    0.24
     Statements
    0.24
     Impossible
    0.23
    naires
    0.23
    Statements
    0.23
    Act Density 0.013%

    No Known Activations