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

    Neuronpedia

    INDEX
    Explanations

    words related to stability and organization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hon
    -0.16
    os
    -0.15
    acet
    -0.15
    oS
    -0.15
     scr
    -0.15
     Kum
    -0.15
    ee
    -0.15
    cell
    -0.14
     denominator
    -0.14
    oe
    -0.14
    POSITIVE LOGITS
    artz
    0.16
    .scalablytyped
    0.16
    ragen
    0.16
    asher
    0.16
    errals
    0.15
    adt
    0.15
     âĹĦ
    0.14
    .synthetic
    0.14
    /stdc
    0.14
     Depart
    0.14
    Act Density 0.296%

    No Known Activations