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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dimensions and perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .opens
    -0.17
    aris
    -0.16
    RuleContext
    -0.15
    ansa
    -0.15
    iddet
    -0.15
    atego
    -0.15
    ooks
    -0.15
    neh
    -0.15
     èŤ
    -0.14
    ris
    -0.14
    POSITIVE LOGITS
    -wide
    0.22
     wide
    0.20
    Wide
    0.18
    coverage
    0.18
     coverage
    0.18
    wide
    0.17
     Wide
    0.17
     scope
    0.16
     widest
    0.16
    scope
    0.16
    Act Density 0.199%

    No Known Activations