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

    Neuronpedia

    INDEX
    Explanations

    political figures and their affiliations

    oai_token-act-pair · gpt-3.5-turbo

    names of political candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.74
    ãĤº
    -0.70
     Serpent
    -0.70
     LTD
    -0.69
    origin
    -0.66
    requires
    -0.65
    sequence
    -0.63
    involved
    -0.63
     Goat
    -0.63
    OX
    -0.62
    POSITIVE LOGITS
     endors
    1.00
     supporters
    0.92
     voters
    0.89
     Voters
    0.86
     polls
    0.86
     endorsed
    0.85
     endorsements
    0.84
     supporter
    0.84
     campaigned
    0.83
    indal
    0.82
    Act Density 0.055%

    No Known Activations