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

    Neuronpedia

    INDEX
    Explanations

    numeric expressions, particularly percentages and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃl
    -0.15
    ephir
    -0.15
    swick
    -0.14
    nect
    -0.14
     pun
    -0.14
    Ø¢ÙĨ
    -0.14
    inar
    -0.14
    âĶĢâĶĢâĶĢâĶĢ
    -0.14
    ectar
    -0.14
    ninger
    -0.14
    POSITIVE LOGITS
    ucc
    0.19
     Horm
    0.15
    ussy
    0.15
    ums
    0.15
     Bast
    0.14
     Thomson
    0.14
    953
    0.14
    899
    0.14
     Garner
    0.14
    ie
    0.13
    Act Density 0.022%

    No Known Activations