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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise, disappointment, and learning about unfortunate news or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .opendaylight
    -0.14
    andon
    -0.14
     defa
    -0.14
    ukkit
    -0.13
    æ³ģ
    -0.13
    iaux
    -0.13
    /socket
    -0.12
    ione
    -0.12
    alnız
    -0.12
     Phen
    -0.12
    POSITIVE LOGITS
     learn
    0.74
     learns
    0.71
     learned
    0.71
    learn
    0.69
     learning
    0.69
    Learn
    0.63
     Learn
    0.62
     learnt
    0.61
    _learn
    0.59
     Learned
    0.57
    Act Density 0.260%

    No Known Activations