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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting used in citation references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blacks
    -0.14
    ÙĬÙĦÙĬ
    -0.14
    iked
    -0.14
    лаÑģ
    -0.13
    arer
    -0.13
    ép
    -0.13
    ÑĪка
    -0.13
    oute
    -0.13
     Bard
    -0.13
     Ook
    -0.13
    POSITIVE LOGITS
    UnderTest
    0.16
     dair
    0.15
    TouchUpInside
    0.15
    UNT
    0.14
    коÑĤ
    0.14
    eniable
    0.14
    portlet
    0.14
     mak
    0.14
    combe
    0.13
    .viewer
    0.13
    Act Density 0.003%

    No Known Activations