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

    Neuronpedia

    INDEX
    Explanations

    electronic devices and gadgets

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas, in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĤ
    -0.62
    jured
    -0.61
    conom
    -0.59
    rarily
    -0.58
    ruck
    -0.58
    gent
    -0.57
    WP
    -0.55
    usion
    -0.52
    zn
    -0.52
     WP
    -0.52
    POSITIVE LOGITS
     respectively
    1.25
     etc
    1.10
     albeit
    0.90
     whichever
    0.86
     culminating
    0.81
     alas
    0.81
    depending
    0.78
     depending
    0.76
     aka
    0.70
     Euph
    0.67
    Act Density 0.731%

    No Known Activations