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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the experience of living in the US

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.79
    Cordialement
    -0.77
     SEDS
    -0.77
    }}]{
    -0.75
     avoient
    -0.72
     Koto
    -0.72
     feroit
    -0.71
     ainfi
    -0.71
     auroit
    -0.70
     étoient
    -0.69
    POSITIVE LOGITS
     незавершена
    0.57
    ,
    0.49
     great
    0.47
     Be
    0.47
     he
    0.46
     
    0.46
     la
    0.45
     not
    0.45
    eval
    0.44
    stateParams
    0.43
    Act Density 0.384%

    No Known Activations