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

    Neuronpedia

    INDEX
    Explanations

    phrases related to appreciation and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.72
     Learning
    -0.64
    Learning
    -0.62
     exerted
    -0.62
    windowFixed
    -0.60
    adpleegd
    -0.60
    ContentAsync
    -0.59
     estekak
    -0.57
    Feeling
    -0.57
    carried
    -0.56
    POSITIVE LOGITS
     providing
    0.77
     offering
    0.76
     presenting
    0.65
     sharing
    0.64
     supplying
    0.59
     betweenstory
    0.57
    providing
    0.57
     featuring
    0.57
     hosting
    0.57
     broadcasting
    0.55
    Act Density 0.379%

    No Known Activations