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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a progression or timeline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchs
    -0.17
    коз
    -0.15
     Protest
    -0.14
    INGER
    -0.14
    ize
    -0.14
    oppers
    -0.14
    ser
    -0.14
    isen
    -0.14
     Impossible
    -0.14
     INNER
    -0.14
    POSITIVE LOGITS
     buildup
    0.21
     build
    0.20
     run
    0.19
     Build
    0.18
     into
    0.17
     Run
    0.17
    run
    0.16
    Run
    0.16
    -build
    0.16
     upto
    0.16
    Act Density 0.010%

    No Known Activations