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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the progression or development of a narrative or project over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intel
    -0.15
     scal
    -0.15
     overflow
    -0.15
    asca
    -0.15
     jump
    -0.15
    ï¸
    -0.15
    inski
    -0.14
     Start
    -0.14
     twice
    -0.14
    .synthetic
    -0.14
    POSITIVE LOGITS
     progressed
    0.28
     progresses
    0.27
     progress
    0.22
    .progress
    0.21
     cÃłng
    0.21
     progressing
    0.20
    progress
    0.20
     Progress
    0.20
     weiter
    0.19
    _progress
    0.19
    Act Density 0.087%

    No Known Activations