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

    Neuronpedia

    INDEX
    Explanations

    statements that convey emotional expression or significant moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (“
    -0.19
     ("\
    -0.16
     ("/
    -0.14
    ivant
    -0.14
    öh
    -0.14
    ostel
    -0.14
    ÐIJÑĢÑħÑĸв
    -0.14
     ("-
    -0.14
    -Ñħ
    -0.14
    коз
    -0.14
    POSITIVE LOGITS
    "And
    0.17
     "
    0.17
    IBE
    0.17
    "But
    0.16
    “And
    0.15
     "(
    0.15
     «
    0.15
     '"
    0.15
    '"
    0.15
    oric
    0.15
    Act Density 0.015%

    No Known Activations