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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate improvement or change in conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritel
    -0.17
    tility
    -0.16
    BOSE
    -0.16
    ινή
    -0.15
    zim
    -0.15
    rone
    -0.15
     MethodInfo
    -0.15
    æĪ¶
    -0.14
    elerik
    -0.14
    zos
    -0.14
    POSITIVE LOGITS
    allel
    0.16
     Mass
    0.15
    ock
    0.14
     Shield
    0.14
    jÄĻ
    0.14
     Maze
    0.14
    ereal
    0.14
    ливÑĸ
    0.14
     chance
    0.14
     Paladin
    0.14
    Act Density 0.071%

    No Known Activations