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

    Neuronpedia

    INDEX
    Explanations

    phrases related to email correspondence

    oai_token-act-pair · gpt-3.5-turbo

    references to mail or mailing-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.90
    tie
    -0.85
    nir
    -0.81
    icians
    -0.77
    meyer
    -0.77
    nor
    -0.75
    pan
    -0.74
    sson
    -0.74
    ende
    -0.71
    nian
    -0.70
    POSITIVE LOGITS
    IL
    1.41
    VE
    1.41
    INT
    1.32
    ISE
    1.31
    IN
    1.26
    BIL
    1.26
    BA
    1.25
    VEN
    1.24
    KE
    1.21
    BI
    1.19
    Act Density 0.053%

    No Known Activations