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

    Neuronpedia

    INDEX
    Explanations

    references to titles or names used in a possessive or descriptive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    룴
    -0.16
    urv
    -0.15
    anne
    -0.15
    idges
    -0.15
    ewise
    -0.14
    precated
    -0.14
    AMS
    -0.14
    foundland
    -0.14
    avl
    -0.13
    еÑĢеж
    -0.13
    POSITIVE LOGITS
     "
    0.23
     '
    0.22
     “
    0.20
     ‘
    0.19
     `
    0.18
     «
    0.17
     "-
    0.15
     viewType
    0.15
    Uploaded
    0.14
     "!
    0.14
    Act Density 0.079%

    No Known Activations