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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awards and sponsorship

    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
    ©¶æ¥µ
    -0.87
    omorphic
    -0.79
    odes
    -0.77
    ema
    -0.74
    senal
    -0.72
    rio
    -0.72
    ront
    -0.72
    imet
    -0.72
    ics
    -0.70
    orts
    -0.70
    POSITIVE LOGITS
     thence
    0.88
    -)
    0.86
     alternatively
    0.85
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.85
     Flavoring
    0.85
     furthermore
    0.83
     moreover
    0.78
     };
    0.75
     yea
    0.74
    âĢ¢âĢ¢
    0.74
    Act Density 0.041%

    No Known Activations