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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical comparisons and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ©
    -0.15
     (£
    -0.14
     (@
    -0.14
     Raj
    -0.14
     offending
    -0.13
    οÏį
    -0.13
     Agents
    -0.13
     exhaustive
    -0.13
     ($
    -0.13
     Sk
    -0.13
    POSITIVE LOGITS
    apore
    0.15
    gee
    0.14
    gings
    0.14
     ÄĮeská
    0.14
    axe
    0.14
    igner
    0.14
    oogle
    0.14
    egie
    0.14
    641
    0.14
    TEGER
    0.13
    Act Density 0.325%

    No Known Activations