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

    Neuronpedia

    INDEX
    Explanations

    the word "for" indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -0.88
     iſt
    -0.85
     raiſ
    -0.82
    BibitemShut
    -0.78
    oredCriteria
    -0.78
    featureID
    -0.77
     purpoſe
    -0.77
    ſelf
    -0.76
    bibfield
    -0.75
     ſind
    -0.75
    POSITIVE LOGITS
     for
    3.02
    for
    2.37
     FOR
    2.31
     For
    2.15
    For
    2.00
     für
    1.93
    FOR
    1.91
     для
    1.90
     voor
    1.85
     για
    1.76
    Act Density 0.544%

    No Known Activations