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

    Neuronpedia

    INDEX
    Explanations

    references to exploitative medical practices involving marginalized communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Css
    -0.15
    ersh
    -0.15
    ÑĨем
    -0.15
    zig
    -0.15
    ÄĻż
    -0.14
    348
    -0.14
    )throws
    -0.14
    лек
    -0.14
    olum
    -0.13
    gem
    -0.13
    POSITIVE LOGITS
     expend
    0.27
     punching
    0.27
     chatt
    0.26
     pawn
    0.23
     disposable
    0.22
     mere
    0.22
     collateral
    0.21
     cannon
    0.21
     convenient
    0.20
    walking
    0.20
    Act Density 0.206%

    No Known Activations