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

    Neuronpedia

    INDEX
    Explanations

    expressions related to preferences and subjective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Damen
    -0.17
    arez
    -0.17
    ̧
    -0.17
    hoe
    -0.15
    abet
    -0.15
    hek
    -0.15
    ứ
    -0.14
     rend
    -0.14
    alternative
    -0.14
     ansch
    -0.14
    POSITIVE LOGITS
    deaux
    0.16
    orp
    0.16
     ties
    0.15
    iesel
    0.15
     fun
    0.15
     zim
    0.15
     closely
    0.15
     subjective
    0.14
    /request
    0.14
    asca
    0.14
    Act Density 0.124%

    No Known Activations