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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities and instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to action, control, and elements of creativity or artistic expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbnails
    -0.71
     Bezos
    -0.63
     millisec
    -0.62
     Elections
    -0.60
     bureaucr
    -0.60
     bribery
    -0.58
     planetary
    -0.57
    ternity
    -0.57
     tides
    -0.57
    unal
    -0.57
    POSITIVE LOGITS
     withd
    1.35
     WITH
    1.30
     with
    1.26
    with
    1.24
    WithNo
    1.14
    With
    1.07
     With
    1.03
    without
    0.97
     WITHOUT
    0.91
    oid
    0.88
    Act Density 0.156%

    No Known Activations