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

    Neuronpedia

    INDEX
    Explanations

    legal terms and phrases related to liability and warranties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erah
    -0.16
    iphy
    -0.16
    imbus
    -0.15
     bullet
    -0.15
    ools
    -0.14
     invert
    -0.14
    invert
    -0.13
    viÄį
    -0.13
     Jud
    -0.13
    conda
    -0.13
    POSITIVE LOGITS
     indirect
    0.30
     consequential
    0.26
     INDIRECT
    0.25
     damages
    0.23
     tort
    0.22
     punitive
    0.22
     dam
    0.21
     Dam
    0.20
    irect
    0.20
     damage
    0.19
    Act Density 0.015%

    No Known Activations