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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to legal or technical details

    oai_token-act-pair · gpt-3.5-turbo

    semicolons in complex informational content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    din
    -0.90
    ront
    -0.80
    izons
    -0.78
    senal
    -0.75
    orts
    -0.75
    ovy
    -0.72
     unbeat
    -0.71
    riet
    -0.71
    agic
    -0.71
    ought
    -0.68
    POSITIVE LOGITS
    -)
    1.06
     thence
    0.95
     furthermore
    0.92
     };
    0.89
     alternatively
    0.87
     moreover
    0.83
     consequently
    0.81
    alias
    0.79
     namely
    0.78
     Flavoring
    0.76
    Act Density 0.051%

    No Known Activations