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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific character sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hon
    -0.19
    eur
    -0.18
    sville
    -0.18
    eum
    -0.17
    eus
    -0.17
    t
    -0.16
    eurs
    -0.16
    eed
    -0.16
    h
    -0.16
    overy
    -0.16
    POSITIVE LOGITS
    sembl
    0.40
    ylum
    0.37
    semblies
    0.37
    bestos
    0.37
    sembled
    0.35
    paragus
    0.34
    pects
    0.34
    sembler
    0.34
    semble
    0.33
    sembling
    0.32
    Act Density 0.036%

    No Known Activations