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

    Neuronpedia

    INDEX
    Explanations

    expressions of insistence or assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erin
    -0.17
    erk
    -0.16
    /player
    -0.15
    rack
    -0.15
     chained
    -0.14
    اگ
    -0.14
    ebek
    -0.14
    اØŃ
    -0.14
     Rag
    -0.14
    hoot
    -0.14
    POSITIVE LOGITS
    ently
    0.30
     upon
    0.21
    ively
    0.19
    antly
    0.18
    ance
    0.16
    ersist
    0.16
     Upon
    0.15
    ONGL
    0.15
    -comp
    0.15
    ANCE
    0.15
    Act Density 0.012%

    No Known Activations