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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating newcomers or beginners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nearest
    -0.15
     mau
    -0.14
    ogue
    -0.14
    eso
    -0.14
     Majority
    -0.14
    itto
    -0.14
    ours
    -0.13
    nearest
    -0.13
    åıĶ
    -0.13
    stad
    -0.13
    POSITIVE LOGITS
    ucher
    0.16
    098
    0.16
    oje
    0.15
    sy
    0.15
    fait
    0.15
     Roose
    0.15
    olly
    0.15
    erdem
    0.14
    erals
    0.14
    erif
    0.14
    Act Density 0.009%

    No Known Activations