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

    Neuronpedia

    INDEX
    Explanations

    commonly used punctuation marks and symbols

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases or clauses within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ishly
    -0.63
    oret
    -0.61
    jah
    -0.55
    phal
    -0.54
    jured
    -0.52
    estone
    -0.52
    rik
    -0.51
    OND
    -0.51
    ingly
    -0.50
    eday
    -0.50
    POSITIVE LOGITS
     respectively
    1.00
     constitutes
    0.94
     is
    0.82
    would
    0.82
     violates
    0.81
     underscores
    0.81
    udeb
    0.80
     seems
    0.80
     amounted
    0.79
     etc
    0.79
    Act Density 0.460%

    No Known Activations