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

    Neuronpedia

    INDEX
    Explanations

    references to raffles or giveaways

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive situations or contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingen
    -0.92
    ynthesis
    -0.90
    ingham
    -0.90
     Wond
    -0.71
    ynt
    -0.70
    sat
    -0.68
    ngth
    -0.66
    itudinal
    -0.66
    agos
    -0.66
    erick
    -0.65
    POSITIVE LOGITS
     vend
    0.77
    hire
    0.70
    ieri
    0.70
     Lash
    0.68
    ulhu
    0.67
    akia
    0.67
    ADS
    0.64
    eteria
    0.62
    coni
    0.61
    rette
    0.61
    Act Density 0.069%

    No Known Activations