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

    Neuronpedia

    INDEX
    Explanations

    elements related to statistics and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cock
    -0.17
    ump
    -0.17
    ãģ°ãģĭãĤĬ
    -0.15
    Spread
    -0.14
    umber
    -0.14
    ër
    -0.14
    óż
    -0.14
    ãĥīãĥ«
    -0.14
    HasBeen
    -0.14
     Spread
    -0.13
    POSITIVE LOGITS
     preparation
    0.20
     preparing
    0.19
     Preparation
    0.17
     prepares
    0.17
     Rot
    0.17
     prepare
    0.17
     Rotation
    0.16
    prep
    0.16
    åĩĨå¤ĩ
    0.16
     rotation
    0.16
    Act Density 0.027%

    No Known Activations