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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decisions or essential factors in a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate dependence or foundational principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.72
    hound
    -0.71
    quer
    -0.69
    bats
    -0.69
    vious
    -0.68
    ibi
    -0.67
    ilk
    -0.67
    upper
    -0.67
    aii
    -0.66
    swick
    -0.66
    POSITIVE LOGITS
     necessity
    0.85
     ensuring
    0.85
     extracting
    0.84
     conviction
    0.84
     respect
    0.84
     convincing
    0.84
     belief
    0.82
     prag
    0.82
     principles
    0.82
     maintaining
    0.80
    Act Density 0.216%

    No Known Activations