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

    Neuronpedia

    INDEX
    Explanations

    mentions of documentation and record-keeping practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     olig
    -0.15
     Keyword
    -0.15
    olean
    -0.14
    /Gate
    -0.14
    .BAD
    -0.14
     Everyday
    -0.13
    ÏĦε
    -0.13
    δÎŃ
    -0.13
     insider
    -0.13
     Exclusive
    -0.13
    POSITIVE LOGITS
    acity
    0.17
    -information
    0.17
    _fields
    0.16
    fields
    0.16
    Fields
    0.16
    /INFO
    0.15
    .bits
    0.15
     Fields
    0.15
     fields
    0.14
    .template
    0.14
    Act Density 0.266%

    No Known Activations