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

    Neuronpedia

    INDEX
    Explanations

    variability and abundance in the information presented, particularly focusing on quantity and alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.20
     YYS
    -0.17
    ottie
    -0.16
    447
    -0.15
    ɵ
    -0.15
    à¸Ńà¸Ķ
    -0.14
    448
    -0.14
    Aliases
    -0.14
    ãĤ°ãĥ©
    -0.13
    rie
    -0.13
    POSITIVE LOGITS
     trick
    0.17
     flags
    0.17
     веÑī
    0.17
     things
    0.16
     fields
    0.16
     flag
    0.16
     tricks
    0.16
     thing
    0.15
    ivate
    0.15
     steps
    0.14
    Act Density 0.274%

    No Known Activations