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

    Neuronpedia

    INDEX
    Explanations

    references to location and direction within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    openConnection
    -0.66
     defaultstate
    -0.64
     &___
    -0.63
    Hentet
    -0.58
    #+#
    -0.58
     szóci
    -0.58
    ⓧ
    -0.57
    SafeMath
    -0.57
     Normdatei
    -0.56
    addCriterion
    -0.54
    POSITIVE LOGITS
     of
    0.82
     thereof
    0.78
     portion
    0.61
     part
    0.56
     duquel
    0.56
     της
    0.54
     kısm
    0.54
    ftagPool
    0.53
     ofthe
    0.52
     Drittel
    0.51
    Act Density 0.282%

    No Known Activations