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

    Neuronpedia

    INDEX
    Explanations

    adjectives with negative connotations, particularly related to social and ethical issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong opinions and assertions about social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intend
    -0.72
     orbits
    -0.70
    çīĪ
    -0.68
     specs
    -0.68
     Explorer
    -0.68
    phrine
    -0.67
     slots
    -0.65
     specifications
    -0.65
     biod
    -0.65
    akeru
    -0.64
    POSITIVE LOGITS
     perpetrated
    1.36
     rampant
    1.30
     rife
    1.22
     abound
    1.08
     contagious
    1.07
     punishable
    1.02
     inflicted
    0.98
     pervasive
    0.97
     prevalent
    0.92
     endemic
    0.92
    Act Density 0.402%

    No Known Activations