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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences containing the word "contains"

    oai_token-act-pair · gpt-3.5-turbo

    text discussing the contents of various items or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tilt
    -0.66
    uchin
    -0.64
    economic
    -0.63
     latch
    -0.63
     axis
    -0.63
    umped
    -0.59
    umping
    -0.59
    hon
    -0.57
     beneficiary
    -0.57
    Enlarge
    -0.56
    POSITIVE LOGITS
     Contains
    1.05
    uggest
    1.02
     contains
    0.91
    ãĤ¼ãĤ¦ãĤ¹
    0.86
    ometimes
    0.86
    ãĤ©
    0.84
    poons
    0.84
    ologne
    0.78
    ences
    0.78
    ngth
    0.77
    Act Density 0.007%

    No Known Activations