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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating numerical limits or thresholds related to age, time, or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gress
    -0.18
    ehler
    -0.16
    mino
    -0.16
    ington
    -0.15
    quan
    -0.15
    setError
    -0.15
    ä¹ħ
    -0.15
    abis
    -0.14
    gow
    -0.14
    ologi
    -0.14
    POSITIVE LOGITS
     (<
    0.24
    ovsky
    0.19
    bird
    0.15
    lings
    0.15
    halb
    0.14
    .orm
    0.14
     Spect
    0.14
    ục
    0.14
    Inflater
    0.13
     seize
    0.13
    Act Density 0.115%

    No Known Activations