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

    Neuronpedia

    INDEX
    Explanations

    technical specifications or product details

    oai_token-act-pair · gpt-3.5-turbo

    product specifications and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     respectively
    -0.71
     downstream
    -0.59
    )."
    -0.59
    .""
    -0.58
     unaff
    -0.55
    ]."
    -0.54
     mere
    -0.53
    .).
    -0.53
     thereof
    -0.53
     upstream
    -0.52
    POSITIVE LOGITS
     Edit
    1.08
    !:
    1.05
     âĵĺ
    1.02
     Profile
    1.00
     :
    0.96
    %:
    0.94
    :
    0.92
    ':
    0.91
     Releases
    0.81
    ¶
    0.81
    Act Density 0.951%

    No Known Activations