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

    Neuronpedia

    INDEX
    Explanations

    phrases related to covering costs or hiding information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     recomm
    -0.71
    rious
    -0.66
    efficients
    -0.65
    nir
    -0.63
    friend
    -0.61
     onwards
    -0.60
     rever
    -0.59
    memory
    -0.58
    Eng
    -0.58
    isoft
    -0.58
    POSITIVE LOGITS
     bases
    0.94
    topic
    0.72
     gaps
    0.71
     entirety
    0.71
    ategories
    0.70
    phia
    0.68
     Mellon
    0.68
     gap
    0.67
    idential
    0.66
    eatures
    0.65
    Act Density 14.474%

    No Known Activations