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

    Neuronpedia

    INDEX
    Explanations

    the presence of numerical ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    innacle
    -0.19
    ukkit
    -0.16
    stown
    -0.16
    uspend
    -0.15
    armac
    -0.15
    âĤĢ
    -0.15
    oufl
    -0.14
    ascade
    -0.14
    immers
    -0.14
    Invariant
    -0.13
    POSITIVE LOGITS
    2
    0.19
    1
    0.17
    3
    0.17
    4
    0.15
    391
    0.15
    ãĥ³ãĥĶ
    0.15
     shade
    0.15
    10
    0.15
     bur
    0.15
    oden
    0.14
    Act Density 0.007%

    No Known Activations