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

    Neuronpedia

    INDEX
    Explanations

    strings of letters or abbreviations in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    symbolic references to entities or institutions associated with education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    683
    -0.80
    ococ
    -0.75
    685
    -0.73
     asbestos
    -0.73
    690
    -0.70
     1870
    -0.69
    hots
    -0.69
    684
    -0.67
     Scarlett
    -0.67
    679
    -0.66
    POSITIVE LOGITS
    D
    1.33
    DD
    1.29
    d
    1.26
    DP
    1.26
    ds
    1.24
    dt
    1.22
    DS
    1.22
    Ds
    1.21
    DR
    1.21
    dor
    1.20
    Act Density 0.728%

    No Known Activations