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

    Neuronpedia

    INDEX
    Explanations

    word combinations that indicate interconnections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conjunctions and their frequency within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "and," especially when used as a conjunction to connect phrases or elements.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
    esterday
    -0.78
     FontFamily
    -0.71
    ardless
    -0.70
    المناصب
    -0.69
    berdayakan
    -0.68
     BoxFit
    -0.67
    ignty
    -0.66
     useAppContext
    -0.66
    polation
    -0.66
    ernalia
    -0.65
    POSITIVE LOGITS
    os
    0.55
    ⓧ
    0.54
    ot
    0.54
    ap
    0.53
    ut
    0.52
    ur
    0.50
    it
    0.50
    jan
    0.50
    ol
    0.49
     own
    0.49
    Act Density 0.214%

    No Known Activations