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

    Neuronpedia

    INDEX
    Explanations

    words related to attention or attraction towards a subject

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seams
    -0.72
    apple
    -0.67
    abby
    -0.66
    é¾į
    -0.64
    aan
    -0.61
    女
    -0.61
    thur
    -0.60
    é¾
    -0.59
    llan
    -0.59
    prus
    -0.59
    POSITIVE LOGITS
    ocene
    0.84
    ATURE
    0.81
    enza
    0.80
    ="#
    0.74
    topic
    0.74
     trolling
    0.73
    edIn
    0.73
     Groups
    0.73
     Interest
    0.72
    Rate
    0.71
    Act Density 0.021%

    No Known Activations