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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditions or contexts for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illo
    -0.15
    ptime
    -0.15
    TTY
    -0.15
    acket
    -0.15
    ilib
    -0.14
     nez
    -0.14
    upa
    -0.14
    ingen
    -0.14
    iless
    -0.14
    ãĥ¥ãĥ¼
    -0.14
    POSITIVE LOGITS
    elden
    0.15
     Awareness
    0.15
    å¦
    0.14
     shed
    0.14
     sheds
    0.14
    229
    0.14
    elsing
    0.14
    ष
    0.13
    lut
    0.13
    lington
    0.13
    Act Density 0.027%

    No Known Activations