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

    Neuronpedia

    INDEX
    Explanations

    words that signify actions or processes, particularly those related to acquisition or accomplishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sterol
    -0.18
    .heroku
    -0.15
    KT
    -0.15
     UNION
    -0.14
    iless
    -0.14
    hower
    -0.14
    ersiz
    -0.14
    egral
    -0.14
    uling
    -0.14
    ypass
    -0.14
    POSITIVE LOGITS
    utely
    0.27
    rimon
    0.26
    quis
    0.26
    oust
    0.25
    quires
    0.25
    umen
    0.25
    quir
    0.25
    rob
    0.25
    acia
    0.24
    erb
    0.23
    Act Density 0.008%

    No Known Activations