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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -1.20
     Roskov
    -1.11
     purpoſe
    -1.09
    Personendaten
    -1.06
    expandindo
    -1.05
    IUrlHelper
    -1.02
     Majefty
    -1.02
     Audiodateien
    -1.01
    AndEndTag
    -1.01
    __':
    -1.01
    POSITIVE LOGITS
    ...
    0.71
     again
    0.70
     
    0.68
     also
    0.66
    ,
    0.65
     of
    0.63
     was
    0.61
     over
    0.61
    ..
    0.60
     in
    0.59
    Act Density 2.065%

    No Known Activations