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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to groups or collections of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ry
    -0.18
    hone
    -0.17
    chl
    -0.15
    igua
    -0.15
    nde
    -0.15
    eri
    -0.15
    /up
    -0.14
    ray
    -0.14
    ifer
    -0.14
    लत
    -0.14
    POSITIVE LOGITS
    ings
    0.32
    think
    0.24
    usc
    0.24
    sWith
    0.20
    ware
    0.19
    INGS
    0.18
    sters
    0.18
     hug
    0.18
    mates
    0.17
    sta
    0.17
    Act Density 0.068%

    No Known Activations