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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "del."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icana
    -0.16
    é¢ĺ
    -0.15
    roe
    -0.15
    ynet
    -0.14
    iface
    -0.14
    ancia
    -0.14
    prar
    -0.14
    erculosis
    -0.14
    avic
    -0.14
    eck
    -0.14
    POSITIVE LOGITS
    uded
    0.24
    uge
    0.23
    usion
    0.23
    ved
    0.22
    iques
    0.21
    ayer
    0.21
    imit
    0.21
    uges
    0.20
    usions
    0.20
    ves
    0.20
    Act Density 0.005%

    No Known Activations