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

    Neuronpedia

    INDEX
    Explanations

    variable assignments and modifications in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leigh
    -0.16
    inel
    -0.16
    ë§Ŀ
    -0.15
     ó
    -0.15
    pj
    -0.15
    nelle
    -0.14
    üt
    -0.14
    رس
    -0.14
    umi
    -0.14
    ecessary
    -0.14
    POSITIVE LOGITS
    ehr
    0.16
    åĸ
    0.16
     Mov
    0.15
     Hoe
    0.15
    mov
    0.14
    otos
    0.14
    ÑĶм
    0.14
    ATUS
    0.14
    cdr
    0.14
    ÏĦαν
    0.14
    Act Density 0.043%

    No Known Activations