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

    Neuronpedia

    INDEX
    Explanations

    references to social and political issues related to women, peace, and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĮ
    -0.17
    aison
    -0.16
    piler
    -0.15
    RICS
    -0.15
    ña
    -0.15
    iÄħ
    -0.14
    peria
    -0.14
    emann
    -0.14
    ngine
    -0.14
    &P
    -0.14
    POSITIVE LOGITS
     matters
    0.18
    ington
    0.17
    olving
    0.15
    idi
    0.15
    azu
    0.15
     Hopkins
    0.15
    0.14
    afür
    0.14
    UEST
    0.14
    matter
    0.14
    Act Density 0.092%

    No Known Activations