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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinion or emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Basic
    -0.41
     Mah
    -0.40
     basic
    -0.40
     Basic
    -0.39
    basic
    -0.39
     fair
    -0.39
     Platten
    -0.38
    Iné
    -0.38
     une
    -0.38
    enter
    -0.38
    POSITIVE LOGITS
     '\\;'
    1.02
    SharedDtor
    0.98
    SequentialGroup
    0.91
    horabuena
    0.89
     архивлан
    0.85
     NSCoder
    0.83
     Infórmanos
    0.79
     hâte
    0.77
     admires
    0.77
     admire
    0.76
    Act Density 0.137%

    No Known Activations