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

    Neuronpedia

    INDEX
    Explanations

    words related to politics and social issues

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "reg" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.81
    LOAD
    -0.69
    ãĥ´ãĤ¡
    -0.65
    DERR
    -0.65
     Tsu
    -0.63
    thia
    -0.61
    ãĥĵ
    -0.61
    INESS
    -0.60
    00200000
    -0.59
    UNCH
    -0.59
    POSITIVE LOGITS
    asus
    1.18
    raphics
    1.13
    roup
    1.05
    entric
    1.00
    lasses
    0.98
    roups
    0.97
    uild
    0.94
    reens
    0.94
    ardless
    0.94
    hetto
    0.93
    Act Density 0.034%

    No Known Activations