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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nomine
    -0.73
    Personensuche
    -0.67
     Majefty
    -0.64
    }?
    -0.61
    ?''
    -0.60
     accordingly
    -0.58
    ?&
    -0.57
     himſelf
    -0.57
    formik
    -0.57
    ltr
    -0.57
    POSITIVE LOGITS
     encanta
    0.72
     wonderful
    0.72
    دانشنامهٔ
    0.71
     encantó
    0.65
     Wur
    0.61
    wonderful
    0.59
     beautiful
    0.59
    ImageContext
    0.58
     love
    0.58
    bbia
    0.57
    Act Density 0.071%

    No Known Activations