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

    Neuronpedia

    INDEX
    Explanations

    names of political figures and their associated actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cellaneous
    -0.54
    emonium
    -0.53
     denotes
    -0.53
    ĸļ
    -0.52
    staking
    -0.51
     Bits
    -0.51
    mble
    -0.50
     prest
    -0.49
    liga
    -0.47
     delighted
    -0.47
    POSITIVE LOGITS
    usterity
    0.64
     encro
    0.63
    xit
    0.62
    Semitism
    0.61
     unpopular
    0.59
     aggression
    0.58
     policies
    0.58
    ocide
    0.57
    arent
    0.57
     aggress
    0.56
    Act Density 1.442%

    No Known Activations