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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases involving less than and greater than thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -1.29
     MainAxisSize
    -1.16
     Efq
    -1.14
    AndEndTag
    -1.13
     Monfieur
    -1.12
    #+#
    -1.11
     raiſ
    -1.11
    RegressionTest
    -1.08
     ſever
    -1.05
     صوتيه
    -1.04
    POSITIVE LOGITS
    lt
    1.87
     lt
    1.00
    LT
    0.97
    gt
    0.69
    olt
    0.65
     LT
    0.62
    elt
    0.60
    l
    0.57
    zu
    0.57
    Gr
    0.56
    Act Density 0.074%

    No Known Activations