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

    Neuronpedia

    INDEX
    Explanations

    negation or the presence of logical conditions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ney
    -0.17
     none
    -0.16
    olley
    -0.15
     not
    -0.15
     nothing
    -0.15
    ança
    -0.14
    otts
    -0.14
    ÙĪÛĮÙĨ
    -0.14
    logg
    -0.14
    ÎķÎł
    -0.14
    POSITIVE LOGITS
    acom
    0.17
    ermann
    0.14
    ëĦ
    0.14
    erre
    0.14
    sWith
    0.14
    ../../../
    0.14
    zano
    0.14
     anymore
    0.13
    idian
    0.13
    yne
    0.13
    Act Density 0.031%

    No Known Activations