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

    Neuronpedia

    INDEX
    Explanations

    organizations or institutions with specific names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doubtless
    -0.73
     swapped
    -0.72
     interfered
    -0.69
     whichever
    -0.68
     indistinguishable
    -0.68
     piled
    -0.67
     scrambling
    -0.67
     accumulated
    -0.66
     disg
    -0.66
     wont
    -0.65
    POSITIVE LOGITS
    :
    1.06
    ¶
    1.02
    ↵
    1.01
     =================================================================
    0.99
     =================================
    0.99
     =================
    0.98
    ?:
    0.98
     :
    0.94
    <|endoftext|>
    0.92
    ↵↵
    0.92
    Act Density 0.265%

    No Known Activations