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

    Neuronpedia

    INDEX
    Explanations

    collective actions and commitments towards social change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äch
    -0.17
     Bid
    -0.14
    rug
    -0.14
    Bid
    -0.13
    ¤ij
    -0.13
    -0.13
    ruc
    -0.13
    oteca
    -0.13
     prepare
    -0.13
    ertificate
    -0.13
    POSITIVE LOGITS
     believe
    0.35
     belief
    0.34
     believed
    0.31
     believes
    0.30
     believing
    0.29
    belief
    0.28
     beliefs
    0.28
     Believe
    0.28
    belie
    0.27
    -bel
    0.26
    Act Density 0.231%

    No Known Activations