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

    Neuronpedia

    INDEX
    Explanations

    technical terms and jargon related to programming and coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lest
    -0.14
    бÑĥдÑĮ
    -0.14
    allow
    -0.14
    ewe
    -0.14
    avenport
    -0.13
     ourselves
    -0.13
    pill
    -0.13
    åĩ¡
    -0.13
    ady
    -0.13
    Īëĭ¤
    -0.13
    POSITIVE LOGITS
     instead
    0.21
     expected
    0.19
     correct
    0.18
    æŃ£ç¡®
    0.17
     my
    0.17
     Expected
    0.16
     correctly
    0.16
     printed
    0.16
     wrong
    0.15
     вмеÑģÑĤ
    0.15
    Act Density 0.156%

    No Known Activations