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

    Neuronpedia

    INDEX
    Explanations

    quoted statements in sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ«
    -0.66
     fairy
    -0.65
     wardrobe
    -0.63
     silhou
    -0.63
     ascended
    -0.63
    animate
    -0.62
     gunfire
    -0.62
     life
    -0.62
     thrill
    -0.62
     scenery
    -0.61
    POSITIVE LOGITS
     Adds
    0.90
     Towards
    0.86
     Additionally
    0.86
    Refer
    0.84
     Refer
    0.82
     Moreover
    0.81
     Furthermore
    0.81
    emphasis
    0.80
     Such
    0.79
    ONSORED
    0.79
    Act Density 0.109%

    No Known Activations