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

    Neuronpedia

    INDEX
    Explanations

    references to carbon-related concepts and their impact on the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urb
    -0.16
    .metamodel
    -0.16
     風
    -0.15
    ivan
    -0.15
    ardown
    -0.15
    acon
    -0.14
    PropertyDescriptor
    -0.14
    รร
    -0.14
    kir
    -0.14
    grounds
    -0.14
    POSITIVE LOGITS
     dioxide
    0.25
    aceous
    0.23
    ates
    0.20
    ated
    0.19
    ized
    0.19
    ioxide
    0.16
    lsru
    0.16
    ne
    0.15
    bero
    0.15
    neau
    0.15
    Act Density 0.020%

    No Known Activations