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

    Neuronpedia

    INDEX
    Explanations

    phrases related to matching criteria or specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APPER
    -0.16
    zion
    -0.16
    orque
    -0.15
    alink
    -0.14
     Zi
    -0.14
    blocking
    -0.14
    abay
    -0.14
    anship
    -0.14
    è¨Ģ
    -0.14
    ahl
    -0.13
    POSITIVE LOGITS
     criteria
    0.21
     Category
    0.20
    èĮĥ
    0.20
     pattern
    0.19
    attern
    0.19
    criteria
    0.19
    -pattern
    0.19
     Criteria
    0.18
    _criteria
    0.18
     category
    0.17
    Act Density 0.097%

    No Known Activations