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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" indicating relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éŃĶ
    -0.80
    !--
    -0.77
    GMT
    -0.75
    Deal
    -0.72
    wic
    -0.71
    uty
    -0.70
    ¶
    -0.68
    utch
    -0.68
    HK
    -0.68
    cipled
    -0.68
    POSITIVE LOGITS
     thus
    1.01
     therefore
    0.98
     consequently
    0.97
     hence
    0.93
     thereby
    0.90
     secondly
    0.84
    romeda
    0.80
    rogen
    0.76
     furthermore
    0.74
     accompanying
    0.72
    Act Density 0.408%

    No Known Activations