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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    949
    -0.15
    aille
    -0.15
     Hod
    -0.15
    æĿī
    -0.14
    pop
    -0.14
    odel
    -0.14
    _except
    -0.14
    idge
    -0.14
     ace
    -0.14
    /pop
    -0.14
    POSITIVE LOGITS
    eniable
    0.18
    quisitions
    0.17
     range
    0.16
     Misc
    0.16
    agrams
    0.16
    urga
    0.16
    upro
    0.15
    range
    0.15
    oÄį
    0.15
    Misc
    0.15
    Act Density 0.323%

    No Known Activations