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

    Neuronpedia

    INDEX
    Explanations

    phrases or clauses beginning with the word "which" followed by a verb in the past or present tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce clauses or point to specific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.66
    ":-
    -0.62
    .",
    -0.60
     discipline
    -0.60
    Fine
    -0.59
    enei
    -0.58
     resil
    -0.58
     ASP
    -0.57
    kell
    -0.56
    +.
    -0.56
    POSITIVE LOGITS
    ãĥ©ãĥ³
    0.94
     incidentally
    0.91
    -)
    0.88
    Downloadha
    0.80
    ãĤ¨ãĥ«
    0.79
    )</
    0.78
    lihood
    0.78
    likely
    0.75
    Ö¼
    0.75
    ardless
    0.74
    Act Density 0.445%

    No Known Activations