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

    Neuronpedia

    INDEX
    Explanations

    sentences that describe definitions or relationships between mathematical concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.81
     CURIAM
    -0.80
     تضيفلها
    -0.76
     MainAxisSize
    -0.72
    הערות
    -0.69
     كومونز
    -0.68
    InvalidProtocol
    -0.67
    ^(@)
    -0.66
     ReactDOM
    -0.62
    msgTypes
    -0.60
    POSITIVE LOGITS
    localScale
    0.53
    ())))
    0.50
     familiar
    0.48
     Normdatei
    0.47
     ramas
    0.46
    сут
    0.44
    BEGIN
    0.44
    foot
    0.44
     esi
    0.43
     classical
    0.43
    Act Density 0.057%

    No Known Activations