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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain conclusive statements or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.71
     Roskov
    -0.71
    }\|
    -0.69
     @}
    -0.67
     disambiguazione
    -0.66
    felf
    -0.64
    তথ্যসূত্র
    -0.64
    "]),
    -0.63
    '}),
    -0.62
    '])->
    -0.60
    POSITIVE LOGITS
     basically
    0.85
     really
    0.85
     stuff
    0.85
     thing
    0.81
    really
    0.81
     things
    0.80
     Basically
    0.79
    Basically
    0.79
     REALLY
    0.76
     dingen
    0.76
    Act Density 0.206%

    No Known Activations