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

    Neuronpedia

    INDEX
    Explanations

    elements related to technical descriptions or instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaults
    -0.15
    повÑĸд
    -0.15
    ãĥ¼ãĥĪ
    -0.15
     kola
    -0.15
    $MESS
    -0.14
    OrNil
    -0.14
    PointSize
    -0.14
    poons
    -0.14
    ì¹
    -0.14
    variants
    -0.14
    POSITIVE LOGITS
     cheap
    0.22
     masking
    0.21
     inexpensive
    0.20
     Harbor
    0.18
    ervo
    0.17
    cheap
    0.17
     McMaster
    0.17
     painters
    0.17
    临
    0.17
     liberal
    0.17
    Act Density 0.160%

    No Known Activations