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

    Neuronpedia

    INDEX
    Explanations

    references to guests or guest-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thal
    -0.16
    ainen
    -0.16
    udit
    -0.16
    ossa
    -0.15
    enta
    -0.15
    ãģ£ãģ±
    -0.15
    annes
    -0.15
    arian
    -0.15
    abeth
    -0.15
    inesis
    -0.15
    POSITIVE LOGITS
    guest
    0.23
     Guest
    0.22
    Guest
    0.21
     guest
    0.21
    imate
    0.20
    imates
    0.19
    èle
    0.19
    imated
    0.18
    imator
    0.17
    marshal
    0.17
    Act Density 0.019%

    No Known Activations