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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or imperatives

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orts
    -0.90
    din
    -0.75
    senal
    -0.75
    wing
    -0.72
    ovy
    -0.70
    abee
    -0.70
    izons
    -0.68
    ussian
    -0.67
     helicop
    -0.67
    ricular
    -0.66
    POSITIVE LOGITS
    -)
    1.18
     namely
    1.15
     whereas
    0.98
     furthermore
    0.93
     hence
    0.91
     Whereas
    0.88
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.88
     moreover
    0.88
    âĢ¢âĢ¢
    0.85
     thence
    0.85
    Act Density 0.052%

    No Known Activations