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

    Neuronpedia

    INDEX
    Explanations

    words related to relationships and connections among people

    oai_token-act-pair · gpt-3.5-turbo

    references to community and kinship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zed
    -0.78
    orius
    -0.70
    ©¶æ
    -0.70
     Launcher
    -0.70
    rique
    -0.68
    edia
    -0.67
    atra
    -0.67
    atche
    -0.66
    ression
    -0.65
    uden
    -0.65
    POSITIVE LOGITS
     spirits
    1.15
     kindred
    1.14
     souls
    0.87
     vein
    0.79
     fractions
    0.79
     sentiments
    0.75
     spirit
    0.74
     strugg
    0.74
    worldly
    0.73
    spir
    0.72
    Act Density 0.028%

    No Known Activations