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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and organizations

    oai_token-act-pair · gpt-3.5-turbo

    prominent names and terms related to contemporary events or controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -+-+
    -0.54
     Sunshine
    -0.54
     destro
    -0.52
    sylv
    -0.51
    eday
    -0.51
     Defin
    -0.51
    ĸļ
    -0.48
     awa
    -0.48
     Surviv
    -0.47
    farious
    -0.46
    POSITIVE LOGITS
     notwithstanding
    0.70
     etc
    0.66
    )?
    0.60
    wise
    0.58
     thereof
    0.57
     defends
    0.56
     thereto
    0.56
     :=
    0.52
     adv
    0.50
     replies
    0.50
    Act Density 0.848%

    No Known Activations