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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology and digital communication

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to technology and societal regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.72
    ĪĴ
    -0.67
    umm
    -0.59
    ä
    -0.58
    yrinth
    -0.58
    Tes
    -0.58
     Mysterious
    -0.56
    ãĥĦ
    -0.56
     Crab
    -0.56
    riad
    -0.56
    POSITIVE LOGITS
     everywhere
    0.96
     altogether
    0.89
     extensively
    0.87
     herself
    0.85
     wherever
    0.84
     itself
    0.83
     myself
    0.81
     anywhere
    0.80
     therapy
    0.78
     ourselves
    0.78
    Act Density 0.326%

    No Known Activations