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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of individuals or characters

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.81
    blance
    -0.71
    enum
    -0.69
    foundation
    -0.67
    ettings
    -0.65
    thood
    -0.64
    192
    -0.63
    PsyNetMessage
    -0.63
    roups
    -0.63
    amsung
    -0.63
    POSITIVE LOGITS
     Conquer
    1.05
     Musical
    1.02
     Elephant
    0.96
     Younger
    0.96
     Beautiful
    0.95
     Monstrous
    0.91
     Whale
    0.90
    orem
    0.89
     Clown
    0.89
     Destroyer
    0.87
    Act Density 0.055%

    No Known Activations