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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "when" and variations related to temporal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITE
    -0.15
    ite
    -0.15
    айÑĤ
    -0.14
    itable
    -0.14
    ynth
    -0.13
    orang
    -0.13
    ục
    -0.13
    aptops
    -0.13
    (#)
    -0.13
    oogle
    -0.13
    POSITIVE LOGITS
    /as
    0.15
    elli
    0.15
    åľŃ
    0.14
    strup
    0.14
    vere
    0.14
    ennen
    0.14
    .Glide
    0.14
    unity
    0.14
    ecal
    0.14
    اØŃÛĮ
    0.13
    Act Density 0.122%

    No Known Activations