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

    Neuronpedia

    INDEX
    Explanations

    instances of legal terminology and conditions related to judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intStringLen
    -0.61
    ględ
    -0.60
    RTDA
    -0.59
    /*
    -0.57
    |}{$
    -0.56
     MainAxisSize
    -0.55
     udaler
    -0.55
    oureuse
    -0.52
    клопе
    -0.52
    #
    -0.51
    POSITIVE LOGITS
     until
    3.87
    until
    3.21
     Until
    3.09
    Until
    3.05
     till
    2.80
     UNTIL
    2.77
     untill
    2.57
     hasta
    2.40
     jusqu
    2.34
    直到
    2.17
    Act Density 0.924%

    No Known Activations