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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the letter 'o' in close proximity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.75
     detrim
    -0.69
     glim
    -0.68
     Salary
    -0.65
     Extras
    -0.61
    REDACTED
    -0.61
     disson
    -0.60
    代
    -0.60
     deficiencies
    -0.59
     Expend
    -0.59
    POSITIVE LOGITS
    opy
    1.42
    pper
    1.23
    gged
    1.07
    gging
    1.07
    opers
    1.04
    aks
    1.04
    zzi
    1.04
    ppo
    1.04
    ppy
    1.04
    veland
    1.03
    Act Density 0.020%

    No Known Activations