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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric or quantitative expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     panel
    -0.16
    core
    -0.15
    gin
    -0.15
     flex
    -0.15
    etine
    -0.13
     panels
    -0.13
    ogle
    -0.13
     environment
    -0.13
     Web
    -0.13
    Environment
    -0.13
    POSITIVE LOGITS
     peacefully
    0.17
    recht
    0.17
    beros
    0.16
     Terr
    0.16
    inspace
    0.16
     franchises
    0.16
    ixer
    0.15
     owed
    0.15
     Recording
    0.15
    iram
    0.15
    Act Density 0.000%

    No Known Activations