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

    Neuronpedia

    INDEX
    Explanations

    references to political and musical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anz
    -0.18
     v
    -0.17
    oven
    -0.17
     overl
    -0.16
     '
    -0.16
    vester
    -0.16
    andle
    -0.15
    ugh
    -0.15
     fro
    -0.15
     posled
    -0.15
    POSITIVE LOGITS
    ujÄħ
    0.23
    ÅĤ
    0.23
    ów
    0.22
    jÄħ
    0.22
    ÅĤa
    0.21
    iÄĻ
    0.21
    że
    0.21
    ÅĽ
    0.21
    ajÄħ
    0.21
    ÅĽcie
    0.21
    Act Density 0.324%

    No Known Activations