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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approximate quantities or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.57
    FRI
    -0.53
    arası
    -0.52
     multiple
    -0.51
    <tr>
    -0.50
     bro
    -0.49
     for
    -0.48
     those
    -0.48
    stra
    -0.47
    chok
    -0.47
    POSITIVE LOGITS
     about
    1.30
    about
    1.22
     ABOUT
    1.12
    bout
    1.06
     About
    1.04
    About
    1.01
     abt
    1.00
    Bout
    0.99
    ABOUT
    0.98
     tungkol
    0.89
    Act Density 0.092%

    No Known Activations