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

    Neuronpedia

    INDEX
    Explanations

    words associated with disruption or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alma
    -0.15
     Ast
    -0.14
     Acer
    -0.14
     Athena
    -0.14
     ALT
    -0.14
    _ALT
    -0.14
     Ashton
    -0.14
     Ay
    -0.14
     Agu
    -0.13
    ãĤ¸ãĤ¢
    -0.13
    POSITIVE LOGITS
    ar
    0.82
    AR
    0.61
    аÑĢ
    0.59
    ars
    0.59
    ár
    0.53
    ार
    0.51
    ار
    0.48
    -ar
    0.47
    âr
    0.46
    ari
    0.45
    Act Density 0.200%

    No Known Activations