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

    Neuronpedia

    INDEX
    Explanations

    titles or subtitles of books or publications

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant experiences or memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :[
    -0.93
    :(
    -0.87
    :-
    -0.87
    ):
    -0.87
     viz
    -0.82
    ]:
    -0.82
    :"
    -0.81
    .):
    -0.81
    ':
    -0.75
    :]
    -0.73
    POSITIVE LOGITS
     Versus
    1.13
     Perspective
    1.11
     Reborn
    1.10
     Lessons
    1.10
     Behind
    1.09
     Begins
    1.09
     Strategies
    1.09
     Experience
    1.07
     Inside
    1.07
     Struggle
    1.06
    Act Density 0.208%

    No Known Activations