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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional situations or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oval
    -0.06
    us
    -0.06
    asley
    -0.06
    ued
    -0.06
    828
    -0.05
    eyn
    -0.05
    SCO
    -0.05
     teb
    -0.05
     display
    -0.05
     aks
    -0.05
    POSITIVE LOGITS
     же
    0.10
    ÑĩаÑģ
    0.09
    zelf
    0.09
    chers
    0.09
    ched
    0.08
    оÑĪ
    0.08
     Angeles
    0.08
     nÃło
    0.08
     ifndef
    0.08
    едини
    0.07
    Act Density 0.008%

    No Known Activations