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

    Neuronpedia

    INDEX
    Explanations

    phrases related to patriotism, equality, and nation-building

    oai_token-act-pair · gpt-3.5-turbo

    themes of equality and civil rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     explan
    -0.57
    uese
    -0.56
    ħĭ
    -0.55
    nesday
    -0.55
     interviewer
    -0.53
    oulos
    -0.51
    assium
    -0.51
    Roll
    -0.51
    PF
    -0.51
    ovember
    -0.51
    POSITIVE LOGITS
     loving
    0.59
     nour
    0.57
    cling
    0.57
     obe
    0.57
     liv
    0.55
     dignity
    0.55
     pleasures
    0.54
     wond
    0.54
    ependent
    0.54
     wonderful
    0.52
    Act Density 1.645%

    No Known Activations