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

    Neuronpedia

    INDEX
    Explanations

    words related to leadership and inspiration

    oai_token-act-pair · gpt-3.5-turbo

    references to investigation or personnel involved in official inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nanto
    -0.83
    DAY
    -0.79
    âĶģ
    -0.77
    DEN
    -0.76
    çĦ
    -0.76
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.69
    town
    -0.68
    WARE
    -0.68
    theless
    -0.67
    Translation
    -0.66
    POSITIVE LOGITS
    iration
    1.60
     Insp
    1.18
    iral
    1.04
    iring
    1.01
    ired
    0.99
    arie
    0.83
    uti
    0.82
    Insp
    0.82
    inia
    0.82
    ires
    0.81
    Act Density 0.010%

    No Known Activations