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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or position relative to the reader

    oai_token-act-pair · gpt-3.5-turbo

    situations and descriptions related to human interactions and feelings of togetherness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    license
    -0.72
     DACA
    -0.69
    ©¶æ
    -0.68
     treaty
    -0.63
     amnesty
    -0.62
     reformed
    -0.62
     certification
    -0.59
    venge
    -0.59
     unilaterally
    -0.58
     reneg
    -0.58
    POSITIVE LOGITS
     passers
    0.78
     buzzing
    0.77
     flickering
    0.71
     scrolling
    0.68
     reminders
    0.68
     subconscious
    0.67
     crowds
    0.67
     gazing
    0.67
     stares
    0.65
    ĸļ
    0.64
    Act Density 1.106%

    No Known Activations