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

    Neuronpedia

    INDEX
    Explanations

    phrases related to compounds and chemical properties

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ITED
    -0.53
    din
    -0.49
    glers
    -0.45
    HCR
    -0.44
    MAX
    -0.43
     Dear
    -0.43
    ^^^^
    -0.42
    stretched
    -0.40
    bnb
    -0.40
     actionGroup
    -0.39
    POSITIVE LOGITS
    otyp
    0.74
    oses
    0.68
    otypes
    0.65
    osing
    0.57
    omen
    0.55
    ipe
    0.55
    omic
    0.54
    osis
    0.53
    ively
    0.53
    oser
    0.53
    Act Density 7.611%

    No Known Activations