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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "made" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLOSE
    -0.68
    arine
    -0.65
    lex
    -0.63
    atin
    -0.60
    Cour
    -0.60
    (){
    -0.59
    Solution
    -0.59
    breaker
    -0.58
    Roaming
    -0.57
    Psy
    -0.57
    POSITIVE LOGITS
     headlines
    1.30
     landfall
    1.14
     waves
    1.04
     clear
    0.91
     sure
    0.89
     mention
    0.84
     abundantly
    0.84
     appearances
    0.83
     noises
    0.82
     strides
    0.79
    Act Density 0.092%

    No Known Activations