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

    Neuronpedia

    INDEX
    Explanations

    the concept of 'change'

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.79
     LIMITED
    -0.77
    ç«
    -0.72
     AFB
    -0.72
    vern
    -0.69
    mination
    -0.68
    ¯¯¯¯
    -0.68
    -+-+
    -0.67
    APH
    -0.66
     Bei
    -0.66
    POSITIVE LOGITS
    overs
    0.88
    over
    0.85
    able
    0.75
    xual
    0.74
     wrought
    0.74
    agents
    0.72
     blindness
    0.71
    making
    0.69
     drastically
    0.67
     radically
    0.67
    Act Density 0.038%

    No Known Activations