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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "plain" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernaut
    -0.18
    gaard
    -0.18
    him
    -0.17
    klad
    -0.16
    naments
    -0.16
    aurus
    -0.16
    amines
    -0.15
    алов
    -0.15
    ampler
    -0.15
    ally
    -0.14
    POSITIVE LOGITS
     jane
    0.28
    clo
    0.24
    chant
    0.24
     vanilla
    0.21
    -ÑĤаки
    0.20
    est
    0.20
     Jane
    0.20
     Vanilla
    0.19
     Dealer
    0.18
    Jane
    0.18
    Act Density 0.012%

    No Known Activations