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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governance and societal structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance and social justice issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.82
    xon
    -0.74
    PsyNetMessage
    -0.68
    \\\\\\\\
    -0.68
     Logged
    -0.68
    Ô
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    fty
    -0.65
     Shed
    -0.64
    çĶ°
    -0.63
    POSITIVE LOGITS
     including
    0.81
     interact
    0.80
     depending
    0.79
     interacted
    0.77
     respectively
    0.76
     interacting
    0.74
     relating
    0.71
     differently
    0.71
     ranging
    0.70
    ilaterally
    0.70
    Act Density 0.337%

    No Known Activations