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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software or technological changes

    oai_token-act-pair · gpt-3.5-turbo

    items and features related to technology and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.67
    anyl
    -0.66
     fantas
    -0.66
     fantasies
    -0.65
    cong
    -0.64
    irgin
    -0.64
     circumst
    -0.63
    ewater
    -0.63
    Virgin
    -0.59
    trump
    -0.59
    POSITIVE LOGITS
     revamped
    1.19
     redesigned
    1.16
     Previously
    1.04
    Removed
    1.04
     renamed
    1.04
     improved
    1.01
    Improved
    1.01
     simplified
    1.00
     revised
    0.99
     Reduced
    0.99
    Act Density 1.031%

    No Known Activations