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

    Neuronpedia

    INDEX
    Explanations

    phrases related to telecommunications and regulations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    din
    -0.87
    ront
    -0.82
    senal
    -0.81
    wald
    -0.74
    rio
    -0.74
    rons
    -0.73
    orts
    -0.73
    urrection
    -0.71
    ric
    -0.71
    formation
    -0.70
    POSITIVE LOGITS
     thence
    1.03
     alternatively
    0.98
     furthermore
    0.96
     consequently
    0.89
     moreover
    0.88
    -)
    0.85
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.85
     hence
    0.77
     };
    0.76
     Flavoring
    0.75
    Act Density 0.049%

    No Known Activations