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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating directions or routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irket
    -0.15
     voksne
    -0.15
    avana
    -0.15
    erin
    -0.15
    cheid
    -0.15
    åĸ
    -0.14
    elder
    -0.14
    ucks
    -0.14
    ult
    -0.14
    razier
    -0.14
    POSITIVE LOGITS
    ovie
    0.14
    OTAL
    0.14
    бин
    0.13
    stad
    0.13
    marvin
    0.13
    oken
    0.13
    tries
    0.13
    noop
    0.13
     Rhe
    0.13
     Addison
    0.13
    Act Density 0.114%

    No Known Activations