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

    Neuronpedia

    INDEX
    Explanations

    references to global coverage or presence

    oai_token-act-pair · gpt-3.5-turbo

    references to global or international contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.80
     Mn
    -0.80
    veyard
    -0.79
    gotten
    -0.74
    enhagen
    -0.72
    imon
    -0.71
    ibility
    -0.69
    tein
    -0.66
     Ging
    -0.66
    IENT
    -0.66
    POSITIVE LOGITS
    ulkan
    0.81
    wide
    0.76
     premiere
    0.76
     Airways
    0.76
     collide
    0.76
     anthem
    0.75
     internationally
    0.72
     globe
    0.71
     unite
    0.70
     Bahá
    0.69
    Act Density 0.037%

    No Known Activations