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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal cases and representation

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names and titles, particularly in a cultural or sporting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.72
     shockingly
    -0.67
     disrespect
    -0.67
     surprisingly
    -0.66
     mustache
    -0.63
     moms
    -0.62
     caution
    -0.62
    ccording
    -0.62
     duplication
    -0.60
     tack
    -0.60
    POSITIVE LOGITS
    liga
    0.83
    wagen
    0.82
     qui
    0.79
    arten
    0.74
     Ãī
    0.73
     Translation
    0.72
    orie
    0.72
    usalem
    0.72
    ;;;;;;;;;;;;
    0.71
    ennes
    0.71
    Act Density 0.235%

    No Known Activations