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

    Neuronpedia

    INDEX
    Explanations

    conditional expressions and discussions about forms and constraints in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erti
    -0.17
    holm
    -0.17
    pio
    -0.15
    oppel
    -0.15
    orte
    -0.14
     duplication
    -0.13
    straints
    -0.13
     artificial
    -0.13
    das
    -0.13
    ema
    -0.13
    POSITIVE LOGITS
    intree
    0.16
    æŁIJ
    0.15
    otr
    0.15
     different
    0.15
    lena
    0.14
    aiser
    0.14
    .want
    0.14
    åĬŀ
    0.14
    imbledon
    0.14
    egl
    0.14
    Act Density 0.095%

    No Known Activations