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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical or scientific notation and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustum
    -0.21
    ATOM
    -0.17
     Cliff
    -0.17
     atom
    -0.16
    .Atomic
    -0.16
    å¾Ĵ
    -0.16
    dge
    -0.15
    arin
    -0.15
    _transition
    -0.15
    umas
    -0.15
    POSITIVE LOGITS
     magnetic
    0.31
     Magnetic
    0.26
     field
    0.26
     fields
    0.25
    ç£ģ
    0.22
     mag
    0.22
     MAG
    0.21
     frozen
    0.21
     tor
    0.20
     FIELD
    0.20
    Act Density 0.072%

    No Known Activations