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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or limitations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shel
    -0.47
    iomanip
    -0.46
    ثل
    -0.45
    Completo
    -0.45
    RenderAtEndOf
    -0.45
    uccess
    -0.45
    čov
    -0.44
     Gouvernement
    -0.44
    EndContext
    -0.44
     approach
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.66
    IntoConstraints
    0.65
     smtplib
    0.62
     Audiodateien
    0.59
     OTHERWISE
    0.57
     otherwise
    0.57
    chitis
    0.57
    +#+
    0.57
     estekak
    0.56
    twimg
    0.56
    Act Density 0.391%

    No Known Activations