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

    Neuronpedia

    INDEX
    Explanations

    actions related to cleaning or restoring conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amber
    -0.16
     Tip
    -0.15
     inter
    -0.15
     Sab
    -0.14
    еÐ
    -0.14
     sab
    -0.14
     Dimit
    -0.14
    tu
    -0.13
    tip
    -0.13
     Div
    -0.13
    POSITIVE LOGITS
    kehr
    0.18
     Tall
    0.16
    bras
    0.16
    iasm
    0.16
     Bras
    0.15
    idle
    0.15
    idon
    0.15
    .mixin
    0.15
    zilla
    0.14
    imation
    0.14
    Act Density 0.370%

    No Known Activations