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

    Neuronpedia

    INDEX
    Explanations

    references to the physical structure and positioning of parts in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icone
    -0.15
    _pen
    -0.14
    æ£
    -0.14
    readcr
    -0.14
    mith
    -0.14
    ród
    -0.13
    /li
    -0.13
    lemen
    -0.13
    razil
    -0.13
    iv
    -0.13
    POSITIVE LOGITS
     portion
    0.26
     portions
    0.21
    portion
    0.19
    -most
    0.19
    most
    0.19
     part
    0.18
    éĥ¨åĪĨ
    0.18
     parte
    0.17
    /top
    0.16
    ë¶Ģë¶Ħ
    0.15
    Act Density 0.094%

    No Known Activations