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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating distance or progress towards a goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a journey or progress towards a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.92
    pecially
    -0.73
    ACTION
    -0.66
    ometimes
    -0.65
     Authors
    -0.65
    Guest
    -0.64
    bol
    -0.63
    cause
    -0.62
     IMAGES
    -0.62
     temp
    -0.61
    POSITIVE LOGITS
     proving
    0.76
     toward
    0.75
     separating
    0.75
     figuring
    0.73
     explaining
    0.70
     overcoming
    0.68
     awaited
    0.67
     towards
    0.67
    izons
    0.67
     recovering
    0.66
    Act Density 0.097%

    No Known Activations