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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "extra" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ponses
    -0.86
     CommandType
    -0.83
    initComponents
    -0.83
    cemic
    -0.81
    )."
    -0.80
     Biosciences
    -0.76
    endpush
    -0.75
    ).'
    -0.75
    PTP
    -0.74
    iseaux
    -0.74
    POSITIVE LOGITS
     extra
    2.34
     Extra
    2.22
     EXTRA
    2.14
    Extra
    2.12
    extra
    2.11
    EXTRA
    1.83
     extras
    1.63
     ekstra
    1.59
     Extras
    1.58
    extras
    1.57
    Act Density 0.050%

    No Known Activations