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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and their surrounding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricanes
    -0.95
    everal
    -0.87
    undai
    -0.83
    rue
    -0.81
    untled
    -0.79
    urrent
    -0.79
    OHN
    -0.79
    20439
    -0.78
    otype
    -0.78
    asio
    -0.77
    POSITIVE LOGITS
     nutshell
    0.84
     Stupid
    0.81
     Tanner
    0.76
     Kinder
    0.73
     ain
    0.69
     huh
    0.67
     yeah
    0.64
     eh
    0.63
     Till
    0.63
     steroids
    0.63
    Act Density 0.498%

    No Known Activations