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

    Neuronpedia

    INDEX
    Explanations

    patterns indicating agreements and interactions in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _mD
    -0.16
    аÑĢод
    -0.16
    ["$
    -0.15
    sein
    -0.15
    roje
    -0.15
    ROTO
    -0.14
    Castle
    -0.14
    _tD
    -0.14
    ืà¸Ļ
    -0.14
    jal
    -0.14
    POSITIVE LOGITS
    505
    0.18
     absolute
    0.15
     Reason
    0.15
    208
    0.15
    bob
    0.15
     epic
    0.14
    130
    0.14
    bond
    0.14
    180
    0.14
    811
    0.14
    Act Density 0.002%

    No Known Activations