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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovol
    -0.16
    anta
    -0.15
    ric
    -0.15
    poons
    -0.14
    tainment
    -0.14
    antor
    -0.14
    ctor
    -0.14
    ono
    -0.14
    iaz
    -0.14
    å¯Ł
    -0.14
    POSITIVE LOGITS
    usch
    0.15
     twice
    0.14
    iendo
    0.14
    de
    0.14
    ornado
    0.14
    into
    0.13
    oby
    0.13
     past
    0.13
    ening
    0.13
    ением
    0.13
    Act Density 0.033%

    No Known Activations