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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "was" in the context of written entries or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acro
    -0.17
    779
    -0.16
    okin
    -0.15
    759
    -0.14
    esser
    -0.14
    eco
    -0.14
    795
    -0.14
    artz
    -0.14
     coder
    -0.13
    _FINE
    -0.13
    POSITIVE LOGITS
    zig
    0.17
    ategories
    0.16
    ıb
    0.15
    ëŀµ
    0.14
     permalink
    0.14
    ackle
    0.14
     Sie
    0.14
    íĥķ
    0.14
    )prepare
    0.14
    infinity
    0.13
    Act Density 0.005%

    No Known Activations