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

    Neuronpedia

    INDEX
    Explanations

    instances of specific technical tasks or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     aquatic
    -0.17
     maritime
    -0.16
     Estr
    -0.15
     ships
    -0.14
    arter
    -0.14
     seaw
    -0.14
    adiens
    -0.14
     naval
    -0.14
     tweet
    -0.14
    iah
    -0.14
    POSITIVE LOGITS
     anchor
    0.27
     anch
    0.25
    anchor
    0.23
    Anchor
    0.23
     anchors
    0.23
    _anchor
    0.23
     anchored
    0.21
    -anchor
    0.20
     Anchor
    0.20
    anchors
    0.20
    Act Density 0.013%

    No Known Activations