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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experiences and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidel
    -0.15
     Washer
    -0.15
    nuts
    -0.15
    izzard
    -0.15
    lec
    -0.14
     elabor
    -0.14
    Wizard
    -0.14
    lum
    -0.13
    545
    -0.13
     hap
    -0.13
    POSITIVE LOGITS
     picks
    0.20
     must
    0.18
     territory
    0.18
     Picks
    0.17
     treat
    0.17
    must
    0.17
     favorites
    0.17
     guilty
    0.17
     pick
    0.17
     favourites
    0.16
    Act Density 0.071%

    No Known Activations