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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software and processes

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to settings, options, and features in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OST
    -0.70
    otos
    -0.64
    condition
    -0.63
    ished
    -0.63
     Schne
    -0.61
    riz
    -0.60
    ISH
    -0.60
     Stern
    -0.59
    stein
    -0.58
    Phys
    -0.58
    POSITIVE LOGITS
    heet
    1.54
    mith
    1.41
    ystem
    1.30
    hift
    1.22
    hare
    1.20
    cape
    1.20
    erver
    1.19
    pace
    1.19
    ilver
    1.19
    pring
    1.18
    Act Density 0.462%

    No Known Activations