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

    Neuronpedia

    INDEX
    Explanations

    specific numbers related to voting results or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those pertaining to statistics or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adjourn
    -0.72
     ladder
    -0.65
     spotlight
    -0.65
     Zel
    -0.64
     drama
    -0.63
     energ
    -0.63
     tomorrow
    -0.62
     destiny
    -0.61
     Hod
    -0.60
     smell
    -0.59
    POSITIVE LOGITS
    95
    3.45
    96
    2.31
    97
    2.30
    93
    2.24
    94
    2.23
    98
    2.19
    90
    2.13
    99
    2.04
    92
    2.01
    85
    1.97
    Act Density 0.030%

    No Known Activations