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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "ew" and its variations in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sto
    -0.07
    mpl
    -0.07
    år
    -0.06
    ackers
    -0.06
    pk
    -0.06
    lej
    -0.06
    ICIAL
    -0.06
    ãģķãģ¾
    -0.06
     Dreams
    -0.06
    ousse
    -0.06
    POSITIVE LOGITS
    ropa
    0.07
    DEX
    0.07
    žen
    0.07
    enden
    0.07
    akens
    0.07
    áng
    0.06
    itness
    0.06
    ings
    0.06
    WSC
    0.06
    riters
    0.06
    Act Density 0.003%

    No Known Activations