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

    Neuronpedia

    INDEX
    Explanations

    words related to transformation or modification

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     slaughtered
    -0.51
    externalActionCode
    -0.49
     marrow
    -0.49
     intest
    -0.48
     swear
    -0.47
    ©¶æ
    -0.47
     caution
    -0.44
    ISO
    -0.43
     reconc
    -0.43
     grandparents
    -0.42
    POSITIVE LOGITS
    icons
    0.96
    ual
    0.96
    ually
    0.95
    ional
    0.95
    ively
    0.93
    ible
    0.90
    acles
    0.89
    ibility
    0.88
    ical
    0.86
    ibles
    0.84
    Act Density 7.615%

    No Known Activations