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

    Neuronpedia

    INDEX
    Explanations

    links or references at the end of a text

    oai_token-act-pair · gpt-3.5-turbo

    links to additional content or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.81
     elim
    -0.76
     misunder
    -0.72
    undai
    -0.71
     trouble
    -0.71
    oud
    -0.71
     exchange
    -0.70
     reservation
    -0.69
    unda
    -0.69
    ridor
    -0.69
    POSITIVE LOGITS
     http
    0.98
     https
    0.97
     Logged
    0.90
     âĨij
    0.83
    76561
    0.83
     Join
    0.80
    http
    0.79
    YES
    0.78
     Provided
    0.78
     Bye
    0.76
    Act Density 0.177%

    No Known Activations