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

    Neuronpedia

    INDEX
    Explanations

    references to forms and data entry instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheon
    -0.15
    argas
    -0.15
    .soft
    -0.14
     iddia
    -0.14
    ahat
    -0.14
    ogg
    -0.14
    akov
    -0.14
    ingu
    -0.14
    éĥ¡
    -0.14
    æľŁ
    -0.14
    POSITIVE LOGITS
     boxes
    0.53
     box
    0.50
     fields
    0.41
     spaces
    0.39
     Boxes
    0.39
    boxes
    0.38
     Box
    0.38
    -box
    0.38
     BOX
    0.36
    box
    0.35
    Act Density 0.103%

    No Known Activations