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

    Neuronpedia

    INDEX
    Explanations

    words related to politics, economy, and global affairs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to immigration and socio-political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ".
    -0.63
    76561
    -0.63
     indo
    -0.62
    _.
    -0.61
    ").
    -0.61
     Aval
    -0.58
    adelphia
    -0.57
    gage
    -0.56
     Seym
    -0.54
    ]."
    -0.53
    POSITIVE LOGITS
     alike
    1.32
    sequent
    0.66
     collide
    0.66
    depending
    0.64
     are
    0.61
     combine
    0.61
    sequently
    0.61
     meanwhile
    0.61
     industries
    0.60
     were
    0.59
    Act Density 0.718%

    No Known Activations