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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erweise
    -0.61
     vectorielles
    -0.56
    Euer
    -0.55
    antMatchers
    -0.55
    UrlResolution
    -0.53
     Hälfte
    -0.52
     âmes
    -0.52
    isation
    -0.51
    eseorang
    -0.51
    Chaque
    -0.50
    POSITIVE LOGITS
    st
    1.22
     others
    1.00
     them
    0.77
     themselves
    0.76
     other
    0.73
     andet
    0.72
    
    0.71
    IsContent
    0.71
     annet
    0.70
    others
    0.68
    Act Density 0.125%

    No Known Activations