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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dependency or reliance on a service or resource

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inez
    -0.18
    angelo
    -0.17
    izontally
    -0.16
    stral
    -0.16
    lement
    -0.16
    dea
    -0.15
    orp
    -0.15
    óż
    -0.15
    itez
    -0.15
    vida
    -0.14
    POSITIVE LOGITS
     upon
    0.37
    Upon
    0.31
     Upon
    0.31
     heavily
    0.30
     heav
    0.29
    upon
    0.28
     heavy
    0.27
     heavier
    0.26
    Heavy
    0.24
     Heavy
    0.23
    Act Density 0.025%

    No Known Activations