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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of correspondents and communication-related terms in news contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -)
    -0.91
     ?)
    -0.79
    )?
    -0.74
    )}
    -0.73
     doesnt
    -0.73
    ?]
    -0.71
     meanwhile
    -0.70
    )</
    -0.70
    )))
    -0.67
    +)
    -0.67
    POSITIVE LOGITS
    —"
    0.70
     proclaiming
    0.68
     frantically
    0.67
    .[
    0.64
     furiously
    0.62
     enthusiastically
    0.62
    —
    0.61
    .
    0.60
     ostensibly
    0.59
     abruptly
    0.58
    Act Density 1.233%

    No Known Activations