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

    Neuronpedia

    INDEX
    Explanations

    numerical values and ratios associated with quantitative data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achen
    -0.16
    orman
    -0.15
    onth
    -0.15
    LESS
    -0.15
    aran
    -0.14
    less
    -0.14
    acha
    -0.14
    BCM
    -0.14
    .Dimension
    -0.14
     Lesser
    -0.14
    POSITIVE LOGITS
     wider
    0.20
     double
    0.18
     triple
    0.18
    ãĤĤãģ£ãģ¨
    0.17
    ÑĨеп
    0.17
     broader
    0.16
     larger
    0.15
    Triple
    0.15
     twice
    0.15
     Double
    0.15
    Act Density 0.127%

    No Known Activations