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

    Neuronpedia

    INDEX
    Explanations

    words related to reduction or decrease

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reduction or decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rieg
    -0.72
    raid
    -0.71
    ullivan
    -0.69
    sol
    -0.64
    RA
    -0.64
    ORE
    -0.63
    lished
    -0.63
    dor
    -0.62
    nell
    -0.62
    ramid
    -0.61
    POSITIVE LOGITS
     proport
    0.81
     dimin
    0.80
    utive
    0.78
     diminish
    0.77
     Jagu
    0.74
    utical
    0.71
    inished
    0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.71
     numb
    0.69
    itized
    0.68
    Act Density 0.023%

    No Known Activations