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

    Neuronpedia

    INDEX
    Explanations

    expressions related to progress or advancement over time

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a journey or process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itton
    -0.82
    oute
    -0.73
    incinn
    -0.72
    encer
    -0.70
    iple
    -0.68
     concess
    -0.68
    avorite
    -0.67
    oggles
    -0.67
     wat
    -0.66
    mare
    -0.64
    POSITIVE LOGITS
    ward
    0.89
    steps
    0.80
    WARD
    0.75
    finding
    0.75
    fare
    0.69
    seeing
    0.63
    aries
    0.61
    stones
    0.61
    point
    0.61
    Step
    0.60
    Act Density 0.013%

    No Known Activations