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

    Neuronpedia

    INDEX
    Explanations

    terms related to competition and joining teams or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDI
    -0.15
    \"",
    -0.14
    BOSE
    -0.14
     nÄĽ
    -0.13
    buz
    -0.13
     "::
    -0.13
     "..
    -0.13
    orie
    -0.12
     ↵↵
    -0.12
    �s
    -0.12
    POSITIVE LOGITS
     ’
    0.80
     '
    0.56
     ‘
    0.46
    -'
    0.44
     âĢ²
    0.44
    ’
    0.38
     ´
    0.37
     \'
    0.37
     `'
    0.36
    /'
    0.32
    Act Density 0.168%

    No Known Activations