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

    Neuronpedia

    INDEX
    Explanations

    legal terms and references related to agreements, rights, and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     such
    -0.18
     ('
    -0.16
    (the
    -0.16
     either
    -0.15
     :↵↵
    -0.15
    ":↵
    -0.15
     the
    -0.15
     :↵
    -0.15
    ':↵
    -0.15
    .the
    -0.15
    POSITIVE LOGITS
     etc
    0.28
    etc
    0.24
     prohibited
    0.21
    çŃī
    0.19
     certain
    0.19
     Certain
    0.19
     forbidden
    0.18
     generally
    0.18
    .—
    0.17
     Generally
    0.16
    Act Density 0.014%

    No Known Activations