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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate progression or actions being taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToScroll
    -0.60
    出版年
    -0.58
    textTheme
    -0.55
    mogat
    -0.54
    gether
    -0.53
     foli
    -0.53
    iyle
    -0.52
     RouterModule
    -0.52
     CIE
    -0.52
     Gij
    -0.51
    POSITIVE LOGITS
     steps
    0.91
     step
    0.82
     Steps
    0.77
     STEPS
    0.76
    steps
    0.74
     passos
    0.67
    BeginContext
    0.66
     pasos
    0.65
    Personendaten
    0.65
     stap
    0.64
    Act Density 0.106%

    No Known Activations