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

    Neuronpedia

    INDEX
    Explanations

    concepts related to processes and actions that have negative or destructive implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azzo
    -0.17
    verity
    -0.16
    ERING
    -0.16
    ÅĽnie
    -0.15
    erule
    -0.15
    aroo
    -0.14
    etwork
    -0.14
    ünkü
    -0.14
    VENTORY
    -0.14
    PLICATION
    -0.14
    POSITIVE LOGITS
    mission
    0.25
    position
    0.22
    press
    0.20
     missions
    0.19
     mission
    0.19
    mitt
    0.19
    mit
    0.17
    Press
    0.17
    lete
    0.16
    pond
    0.15
    Act Density 0.103%

    No Known Activations