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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Ly," indicating a focus on analysis or commentary within broad discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perture
    -0.81
    raints
    -0.75
    ORTS
    -0.74
    sburgh
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.70
    ardless
    -0.68
    DERR
    -0.68
    ajor
    -0.67
    LESS
    -0.67
    ULTS
    -0.67
    POSITIVE LOGITS
    onel
    0.98
    nda
    0.94
    rics
    0.93
    nton
    0.93
    mb
    0.87
    gg
    0.85
    comed
    0.84
    bian
    0.81
    onna
    0.81
    lla
    0.80
    Act Density 0.004%

    No Known Activations