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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics and hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal roles and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -0.61
    anton
    -0.61
     disclaim
    -0.61
     catast
    -0.60
    leigh
    -0.59
    ensions
    -0.57
    laws
    -0.57
    imar
    -0.57
    irin
    -0.57
    ritz
    -0.57
    POSITIVE LOGITS
     fodder
    0.84
     extraord
    0.76
     unto
    0.69
     alongside
    0.67
    .(
    0.67
     asset
    0.66
     amidst
    0.65
     beacon
    0.64
     forever
    0.62
     centerpiece
    0.62
    Act Density 0.480%

    No Known Activations