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

    Neuronpedia

    INDEX
    Explanations

    words related to specific locations and their hierarchical or structural characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ip
    -0.15
    ous
    -0.15
    acios
    -0.14
    amba
    -0.14
    icator
    -0.14
     disp
    -0.14
    wed
    -0.14
     groom
    -0.13
    okie
    -0.13
    ippet
    -0.13
    POSITIVE LOGITS
     culpa
    0.21
    urement
    0.19
    UREMENT
    0.18
    anine
    0.17
    ENDOR
    0.16
    orable
    0.15
    apixel
    0.15
    (Me
    0.15
     Moy
    0.15
    anical
    0.15
    Act Density 0.024%

    No Known Activations