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

    Neuronpedia

    INDEX
    Explanations

    university and college names

    oai_token-act-pair · gpt-3.5-turbo

    specific university names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ococ
    -0.80
    683
    -0.79
    679
    -0.77
    690
    -0.76
    685
    -0.75
    69
    -0.73
    691
    -0.72
    ols
    -0.72
    684
    -0.71
    ãĥĻ
    -0.68
    POSITIVE LOGITS
    dor
    1.19
    DM
    1.17
    DE
    1.13
    D
    1.13
    DD
    1.11
    dt
    1.10
    dl
    1.10
     DD
    1.10
    dm
    1.09
    der
    1.09
    Act Density 0.595%

    No Known Activations