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

    Neuronpedia

    INDEX
    Explanations

    quotations or statements, often expressing strong emotional or opinionated views

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gettable
    -0.78
     coerc
    -0.78
     therap
    -0.69
     neighb
    -0.69
     overloaded
    -0.68
     challeng
    -0.65
     oun
    -0.64
    ¥ŀ
    -0.64
    icer
    -0.64
    °
    -0.64
    POSITIVE LOGITS
     âĢķ
    1.03
     Said
    0.91
     Adds
    0.81
     –
    0.80
     Translation
    0.79
     Huh
    0.78
     Asked
    0.77
     Saying
    0.77
     Appears
    0.76
     -
    0.75
    Act Density 0.079%

    No Known Activations