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

    Neuronpedia

    INDEX
    Explanations

    adjectives or characteristics describing a person

    oai_token-act-pair · gpt-3.5-turbo

    references to personal qualities and attributes of a man, often highlighting both positive and negative traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trickle
    -0.76
     thwart
    -0.70
     coincide
    -0.69
     Mobil
    -0.68
     funnel
    -0.67
     contingency
    -0.67
     geography
    -0.67
     overlap
    -0.66
     converge
    -0.66
     discrep
    -0.65
    POSITIVE LOGITS
    ves
    1.25
    ems
    1.10
    ses
    1.07
    gets
    1.04
    ï¸ı
    1.03
    s
    1.02
    dies
    0.98
    ufact
    0.98
    his
    0.97
    ates
    0.96
    Act Density 0.141%

    No Known Activations