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

    Neuronpedia

    INDEX
    Explanations

    parts or regions within a larger entity

    oai_token-act-pair · gpt-3.5-turbo

    references to various regions or segments of a broader context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulus
    -0.58
    ampa
    -0.55
     invitation
    -0.54
    odore
    -0.54
    balance
    -0.54
    adem
    -0.52
    weights
    -0.52
     Ladies
    -0.51
    osen
    -0.51
     bombshell
    -0.50
    POSITIVE LOGITS
     of
    1.28
     thereof
    1.23
    of
    0.90
    pace
    0.87
    Of
    0.84
    cale
    0.81
     Of
    0.81
    hops
    0.81
    paces
    0.78
     OF
    0.76
    Act Density 0.197%

    No Known Activations