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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases and references to issues and injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ione
    -0.78
    ivers
    -0.69
    inav
    -0.68
    Awesome
    -0.67
     enthusiastically
    -0.65
    ISSION
    -0.65
     nods
    -0.62
     reperto
    -0.62
    ilion
    -0.61
     Zup
    -0.61
    POSITIVE LOGITS
     hinder
    1.35
     hindered
    1.32
     hampered
    1.31
     plague
    1.29
     plagued
    1.24
     prevented
    1.21
     impede
    1.20
     hind
    1.14
     complicate
    1.11
     preclude
    1.10
    Act Density 0.227%

    No Known Activations