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

    Neuronpedia

    INDEX
    Explanations

    words associated with political actions and investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovah
    -0.20
    OGLE
    -0.17
    opak
    -0.17
    onte
    -0.15
    Lookup
    -0.15
    rott
    -0.14
    æ¦ľ
    -0.14
    auer
    -0.14
    ovie
    -0.14
    edad
    -0.14
    POSITIVE LOGITS
    anch
    0.16
    amage
    0.15
    his
    0.15
    mens
    0.15
    azio
    0.14
    Invariant
    0.14
     AG
    0.14
     Cir
    0.14
     Fox
    0.14
    Äįka
    0.14
    Act Density 0.032%

    No Known Activations