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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing resistance or susceptibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erto
    -0.17
    reck
    -0.16
    bons
    -0.15
    erah
    -0.15
    ierce
    -0.15
    meni
    -0.14
    937
    -0.14
    yro
    -0.14
     Kostenlose
    -0.14
    eki
    -0.14
    POSITIVE LOGITS
    gether
    0.16
    asting
    0.15
    ledo
    0.14
    asty
    0.14
     nov
    0.14
     Keeper
    0.13
    extr
    0.13
     Crimes
    0.13
    col
    0.13
     extr
    0.13
    Act Density 0.200%

    No Known Activations