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

    Neuronpedia

    INDEX
    Explanations

    the presence of instances of the substring "sp" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mente
    -0.15
    IVITY
    -0.15
    letes
    -0.15
    nette
    -0.14
    ém
    -0.14
     spare
    -0.14
    ey
    -0.14
    IDAD
    -0.14
    anford
    -0.14
    estro
    -0.14
    POSITIVE LOGITS
    okes
    0.36
    atial
    0.32
    reading
    0.30
    ouse
    0.29
    oke
    0.29
    oken
    0.28
    ouses
    0.28
    awning
    0.27
    aced
    0.27
    arsity
    0.26
    Act Density 0.021%

    No Known Activations