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

    Neuronpedia

    INDEX
    Explanations

    phrases that express collective identity and perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nakalista
    -0.73
     ujednoznacz
    -0.65
     queſta
    -0.60
     ―――――
    -0.52
     Craw
    -0.51
    ロウィン
    -0.50
    ſammen
    -0.50
    rungsseite
    -0.50
     actionMode
    -0.50
     TZ
    -0.50
    POSITIVE LOGITS
     teníamos
    0.45
    hadapi
    0.39
     styr
    0.36
     hoped
    0.36
     esperan
    0.36
    nalpot
    0.36
     Rücks
    0.35
     ramach
    0.35
     estable
    0.35
     jsme
    0.35
    Act Density 0.245%

    No Known Activations