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

    Neuronpedia

    INDEX
    Explanations

    mentions of blog posts or articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific non-standard characters or symbols often used in media titles or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sacrific
    -0.83
     miscar
    -0.69
     Medline
    -0.63
     UD
    -0.61
     Tanz
    -0.61
     Misc
    -0.60
    oche
    -0.60
     fert
    -0.60
     Yon
    -0.58
     vulner
    -0.58
    POSITIVE LOGITS
    ï¸ı
    0.93
    ¯
    0.82
     environment
    0.76
    framework
    0.75
    esque
    0.74
    s
    0.74
     moniker
    0.73
    ship
    0.73
    #$
    0.72
     logo
    0.70
    Act Density 0.178%

    No Known Activations