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

    Neuronpedia

    INDEX
    Explanations

    references to guidance and advising within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vince
    -0.15
    vection
    -0.15
    kul
    -0.15
    ieren
    -0.14
    isen
    -0.14
    loud
    -0.14
    lé
    -0.14
     bitwise
    -0.14
    UpInside
    -0.14
    kili
    -0.14
    POSITIVE LOGITS
     shape
    0.20
     towards
    0.20
     toward
    0.19
    shape
    0.18
     shaped
    0.18
    -shaped
    0.17
     guide
    0.16
    (shape
    0.16
     shaping
    0.16
    ux
    0.15
    Act Density 0.082%

    No Known Activations