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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global news and events

    oai_token-act-pair · gpt-3.5-turbo

    references to global topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.85
    veyard
    -0.81
    odox
    -0.80
    iosyn
    -0.79
     Mn
    -0.75
    enhagen
    -0.71
    gotten
    -0.70
    utenant
    -0.68
    ibility
    -0.66
    iple
    -0.65
    POSITIVE LOGITS
     Airways
    0.77
     illegally
    0.73
     ambassador
    0.71
     collide
    0.71
     premiere
    0.70
     converge
    0.70
     worldwide
    0.69
    JD
    0.67
     Bahá
    0.67
     roaming
    0.66
    Act Density 0.058%

    No Known Activations