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

    Neuronpedia

    INDEX
    Explanations

    phrases related to feedback and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nee
    -0.17
    walker
    -0.14
    nech
    -0.14
    deen
    -0.14
    žÃŃt
    -0.13
     맡
    -0.13
    enor
    -0.13
    auer
    -0.13
    ίγ
    -0.13
    ornment
    -0.13
    POSITIVE LOGITS
     informed
    0.22
     better
    0.22
     inform
    0.21
     informs
    0.20
     flag
    0.20
     spot
    0.19
     fine
    0.19
     recommendations
    0.19
     guide
    0.19
     pro
    0.19
    Act Density 0.306%

    No Known Activations