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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate important conditions or factors, often evaluating significance or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apos
    -0.15
    ilter
    -0.15
    ØŃص
    -0.15
    lero
    -0.15
     Král
    -0.14
    ÙĬÙĪÙĨ
    -0.14
    emouth
    -0.14
    erval
    -0.14
    anship
    -0.14
    imits
    -0.13
    POSITIVE LOGITS
    chein
    0.15
    Porn
    0.15
    ä»
    0.15
    agina
    0.14
    -pill
    0.14
    imli
    0.13
    needle
    0.13
    ³
    0.13
    èĤī
    0.13
     showc
    0.13
    Act Density 0.102%

    No Known Activations