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

    Neuronpedia

    INDEX
    Explanations

    descriptions of performance quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usta
    -0.21
    291
    -0.16
    ards
    -0.16
    REW
    -0.15
    rippling
    -0.15
    sha
    -0.15
    rew
    -0.14
    esta
    -0.14
    akes
    -0.14
    icip
    -0.14
    POSITIVE LOGITS
    peak
    0.18
     peak
    0.18
    Peak
    0.17
     usual
    0.16
     Hodg
    0.16
     Peak
    0.15
    pone
    0.15
     mood
    0.15
    /XMLSchema
    0.14
    undry
    0.14
    Act Density 0.167%

    No Known Activations