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

    Neuronpedia

    INDEX
    Explanations

    phrases that express opinions or evaluations about experiences and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elman
    -0.16
    .ly
    -0.15
    EI
    -0.15
    oor
    -0.15
    imen
    -0.15
    enment
    -0.15
     Vog
    -0.15
    ride
    -0.15
    oho
    -0.15
    ufs
    -0.14
    POSITIVE LOGITS
    ANA
    0.16
    haul
    0.15
     Sass
    0.15
     degrees
    0.14
    asion
    0.14
    üt
    0.14
    ÑĥÑĤи
    0.14
     carn
    0.14
    etes
    0.14
    opsis
    0.13
    Act Density 0.171%

    No Known Activations