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

    Neuronpedia

    INDEX
    Explanations

    words related to intelligence and mental abilities

    oai_token-act-pair · gpt-3.5-turbo

    words associated with obstruction or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XY
    -0.74
    Connector
    -0.70
    bial
    -0.70
    Accessory
    -0.65
    ĸļ
    -0.62
     Dynamics
    -0.61
    Cam
    -0.60
    Aid
    -0.59
    Steven
    -0.59
    Story
    -0.59
    POSITIVE LOGITS
    icter
    0.77
    iu
    0.77
    iddling
    0.74
    edi
    0.73
    yll
    0.71
    itial
    0.70
    qi
    0.70
    amba
    0.68
    icion
    0.68
     exting
    0.67
    Act Density 0.055%

    No Known Activations