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

    Neuronpedia

    INDEX
    Explanations

    words related to maximum and minimum measurements or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OUGH
    -0.18
    egend
    -0.15
     suf
    -0.15
    lijah
    -0.15
    ÅĽli
    -0.15
    ÑĢава
    -0.15
    ough
    -0.14
    èģ
    -0.14
    osex
    -0.14
    anager
    -0.14
    POSITIVE LOGITS
    imize
    0.49
    imal
    0.47
    ima
    0.42
    imized
    0.42
    imizer
    0.42
    imo
    0.40
    imum
    0.37
    ime
    0.37
    IMUM
    0.36
    ималÑĮ
    0.34
    Act Density 0.024%

    No Known Activations