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

    Neuronpedia

    INDEX
    Explanations

    themes related to advocacy and social issues in presentations and papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Install
    -0.16
    ÙĤب
    -0.14
    ControlEvents
    -0.14
    faker
    -0.14
    Attempt
    -0.13
    ptrdiff
    -0.13
    Pick
    -0.13
     attempt
    -0.13
     uplift
    -0.13
    olv
    -0.13
    POSITIVE LOGITS
     Tow
    0.20
     Towards
    0.19
     Address
    0.18
    Towards
    0.17
     Beyond
    0.17
     building
    0.17
    -chart
    0.17
     towards
    0.17
     toward
    0.16
     Building
    0.16
    Act Density 0.136%

    No Known Activations