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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies or data analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $$$$
    -0.74
    ¬¼
    -0.69
    Shut
    -0.69
    )}
    -0.69
    rolet
    -0.68
    iour
    -0.67
    Äĵ
    -0.67
    atra
    -0.66
    itol
    -0.66
    ãģł
    -0.65
    POSITIVE LOGITS
     researchers
    1.12
     psychologists
    0.98
     analysts
    0.98
     analyzing
    0.95
     scholars
    0.95
     researcher
    0.87
     psychologist
    0.87
     determining
    0.85
     historian
    0.85
     evaluating
    0.84
    Act Density 0.119%

    No Known Activations