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

    Neuronpedia

    INDEX
    Explanations

    words related to references or the act of mentioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Accessor
    -0.17
    ville
    -0.17
    ourd
    -0.16
    igh
    -0.16
    vig
    -0.16
    ylon
    -0.15
    ht
    -0.15
    aju
    -0.15
    ilde
    -0.15
    vu
    -0.15
    POSITIVE LOGITS
    entially
    0.24
    ential
    0.24
    encing
    0.22
     specifically
    0.19
    erring
    0.18
    rence
    0.18
     back
    0.18
    endum
    0.18
    ensi
    0.17
    enced
    0.17
    Act Density 0.018%

    No Known Activations