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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision making and selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usher
    -0.16
    phinx
    -0.16
     Fo
    -0.16
     excess
    -0.15
     Foundation
    -0.14
     un
    -0.13
     Arn
    -0.13
     Cage
    -0.13
    egen
    -0.13
     att
    -0.13
    POSITIVE LOGITS
    åĪ»
    0.16
    lla
    0.15
    otas
    0.14
    _hooks
    0.14
    orizontal
    0.14
    enko
    0.14
    .scalablytyped
    0.14
    ATAB
    0.13
    Rew
    0.13
    -meta
    0.13
    Act Density 0.033%

    No Known Activations