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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community organizations and their goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.78
     dodgy
    -0.75
     weirdly
    -0.73
     pretty
    -0.72
     sneaky
    -0.68
     messed
    -0.67
    paramref
    -0.66
     tweaked
    -0.66
    3
    -0.64
     let
    -0.64
    POSITIVE LOGITS
     photolibrary
    1.18
     ་་
    1.15
     itſelf
    1.14
     myſelf
    1.09
     Jefus
    1.08
     ―――――
    1.08
     ſind
    1.05
     Efq
    1.04
     pleaſure
    1.03
    ſelf
    1.03
    Act Density 0.318%

    No Known Activations