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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical calculations and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nest
    -0.15
    rame
    -0.15
    ibri
    -0.15
     Hlav
    -0.14
     Dag
    -0.14
    .RightToLeft
    -0.14
     Nest
    -0.13
    illance
    -0.13
    avy
    -0.13
    olet
    -0.13
    POSITIVE LOGITS
     numbers
    0.69
    numbers
    0.57
     Numbers
    0.56
     number
    0.53
    Numbers
    0.52
    _numbers
    0.50
    -num
    0.49
    æķ°åŃĹ
    0.48
     ÑĩиÑģла
    0.46
    -number
    0.46
    Act Density 0.194%

    No Known Activations