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

    Neuronpedia

    INDEX
    Explanations

    instances of words associated with public or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umble
    -0.16
    ivals
    -0.15
    alo
    -0.15
    unta
    -0.15
    ManagerInterface
    -0.15
    _manifest
    -0.14
    ahren
    -0.14
    avel
    -0.14
    DirectoryName
    -0.14
    ope
    -0.14
    POSITIVE LOGITS
    anch
    0.21
     spark
    0.18
    ANCH
    0.18
    agal
    0.16
    anchor
    0.16
    urum
    0.15
     anch
    0.15
     anchor
    0.15
    ady
    0.15
    defgroup
    0.15
    Act Density 0.028%

    No Known Activations