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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of obligation or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æk
    -0.15
    efficient
    -0.14
    ibold
    -0.14
    agos
    -0.13
    ικÏĮ
    -0.13
    uj
    -0.13
    .addRow
    -0.13
    ycastle
    -0.13
    -efficient
    -0.13
    ault
    -0.13
    POSITIVE LOGITS
     need
    0.27
     worries
    0.24
     strings
    0.24
     worry
    0.23
     muss
    0.23
    need
    0.22
     obligation
    0.22
     hidden
    0.21
     необÑħодимоÑģÑĤи
    0.21
     commitment
    0.21
    Act Density 0.136%

    No Known Activations