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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of "Alpha" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of Greek letters or their associated fraternal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gown
    -0.69
    sson
    -0.68
     WTO
    -0.68
     covered
    -0.67
    olkien
    -0.65
     UNESCO
    -0.65
    tty
    -0.65
    arrell
    -0.64
    whel
    -0.63
     Sloven
    -0.63
    POSITIVE LOGITS
     Alpha
    3.90
    Alpha
    3.15
     Beta
    2.45
     alpha
    2.31
     Gamma
    2.31
    alpha
    2.19
    Beta
    2.04
     Omega
    2.00
     Sigma
    1.75
    beta
    1.61
    Act Density 0.027%

    No Known Activations