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

    Neuronpedia

    INDEX
    Explanations

    examples or instances of various contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparative phrases and examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.69
     tyr
    -0.60
     Defendants
    -0.58
     DPR
    -0.53
     CY
    -0.51
     ventilation
    -0.51
    theless
    -0.51
    ailability
    -0.50
     Conversation
    -0.50
     spiders
    -0.50
    POSITIVE LOGITS
    .,
    0.92
    ,
    0.85
    ,,
    0.75
    displayText
    0.75
    *,
    0.68
    opt
    0.66
    è£ħ
    0.66
    !,
    0.65
    ãĢģ
    0.63
    innie
    0.63
    Act Density 0.066%

    No Known Activations