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

    Neuronpedia

    INDEX
    Explanations

    references to permission or the act of seeking approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anſ
    -0.75
     Perſ
    -0.67
     purpoſe
    -0.65
    ագրություններ
    -0.63
     Conſ
    -0.60
     Reſ
    -0.58
     auber
    -0.57
     Inſ
    -0.57
     ſind
    -0.57
     uſe
    -0.57
    POSITIVE LOGITS
     mijne
    0.62
     positively
    0.48
    #!/
    0.47
     betrekking
    0.46
     egens
    0.44
     continuación
    0.44
     jongen
    0.43
     bienvenida
    0.43
     peccato
    0.42
     helft
    0.42
    Act Density 0.220%

    No Known Activations