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

    Neuronpedia

    INDEX
    Explanations

    references to lists and rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajas
    -0.14
     Rule
    -0.14
     pill
    -0.14
    feld
    -0.14
    uster
    -0.14
    Rule
    -0.13
     host
    -0.13
     Left
    -0.13
     rule
    -0.13
     split
    -0.13
    POSITIVE LOGITS
     γαÏģ
    0.18
    APH
    0.15
    Äįan
    0.15
    ãĤĮãģ©
    0.15
    omid
    0.14
    Truthy
    0.14
    plx
    0.14
    hani
    0.14
    OfSize
    0.14
    anco
    0.14
    Act Density 0.231%

    No Known Activations