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

    Neuronpedia

    INDEX
    Explanations

    references to political entities, such as legislative bills, politicians, and political parties

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the letter "S" at the beginning of sentences or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.69
    steen
    -0.67
     Eternity
    -0.65
    enhagen
    -0.65
    enegger
    -0.64
    rities
    -0.63
    blers
    -0.63
    bart
    -0.61
    ãĥ¼ãĤ¯
    -0.61
    ocaust
    -0.61
    POSITIVE LOGITS
    pta
    0.76
    xual
    0.69
    omon
    0.68
     Forces
    0.68
    atoon
    0.67
    士
    0.65
    OPE
    0.62
    pport
    0.61
    RP
    0.60
    RET
    0.60
    Act Density 0.063%

    No Known Activations