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

    Neuronpedia

    INDEX
    Explanations

    words related to user interactions or commands on digital platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.13
     Efq
    -1.10
     Theſe
    -1.08
     Monfieur
    -1.05
     ModelExpression
    -1.02
     Houſe
    -1.01
     ―――――
    -1.01
     Jefus
    -1.00
     Anſ
    -0.99
     myſelf
    -0.99
    POSITIVE LOGITS
     in
    1.39
     In
    1.25
     в
    1.24
    In
    1.07
     IN
    1.03
     into
    0.94
     В
    0.94
     în
    0.92
     dalam
    0.90
     في
    0.84
    Act Density 0.050%

    No Known Activations