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

    Neuronpedia

    INDEX
    Explanations

    semicolons at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    semicolons in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spons
    -0.86
    orts
    -0.86
    izons
    -0.79
    din
    -0.74
    thal
    -0.74
     helicop
    -0.74
    agic
    -0.72
    senal
    -0.72
    bledon
    -0.71
    ovy
    -0.69
    POSITIVE LOGITS
    -)
    1.13
     namely
    1.03
    }:
    0.89
     whereas
    0.89
     };
    0.86
    }"
    0.83
    âĢ¢âĢ¢
    0.83
     Whereas
    0.81
     thence
    0.80
     furthermore
    0.79
    Act Density 0.058%

    No Known Activations