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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the presence or significance of specific elements or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opr
    -0.17
    rompt
    -0.15
    arendra
    -0.15
    ivent
    -0.14
    ifice
    -0.14
    identity
    -0.14
    ALAR
    -0.14
    .easing
    -0.13
     roster
    -0.13
    iven
    -0.13
    POSITIVE LOGITS
    iola
    0.15
    erb
    0.15
    ÅŁÄ±
    0.14
     XCT
    0.14
    640
    0.14
    ote
    0.13
     ëģ
    0.13
    ented
    0.13
    bilt
    0.13
    Sparse
    0.13
    Act Density 0.053%

    No Known Activations