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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and justice

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to issues of justice and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achev
    -0.79
    Äĩ
    -0.76
    earable
    -0.76
    alach
    -0.74
    daq
    -0.74
    xual
    -0.72
    KO
    -0.71
    qqa
    -0.70
    natureconservancy
    -0.69
    ACP
    -0.68
    POSITIVE LOGITS
     souls
    0.91
     brethren
    0.90
     wisdom
    0.87
     glory
    0.86
     riches
    0.82
     earthly
    0.78
    ness
    0.77
    itude
    0.77
     mortal
    0.76
     blessings
    0.76
    Act Density 0.221%

    No Known Activations