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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tips or clever methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     å©
    -0.15
    ivement
    -0.14
    iams
    -0.14
    iegel
    -0.14
    erah
    -0.14
    StringRef
    -0.14
    .Encoding
    -0.14
     fid
    -0.14
    .metro
    -0.13
    jadi
    -0.13
    POSITIVE LOGITS
    ë§IJ
    0.17
    ades
    0.15
    ston
    0.14
    acular
    0.14
     Dome
    0.14
    yr
    0.14
    sters
    0.14
     Lon
    0.14
    ade
    0.14
    fort
    0.14
    Act Density 0.006%

    No Known Activations