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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positive reactions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĪев
    -0.15
    çĢ
    -0.14
    /cs
    -0.14
     frec
    -0.14
    esteem
    -0.14
     æĽ
    -0.14
     dialogs
    -0.13
    arie
    -0.13
     Olympics
    -0.13
    Serializable
    -0.13
    POSITIVE LOGITS
     Player
    0.17
     Elite
    0.17
     player
    0.17
    ju
    0.16
    apos
    0.16
     elite
    0.15
     personnel
    0.15
    URRED
    0.15
     players
    0.14
    /player
    0.14
    Act Density 0.621%

    No Known Activations