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

    Neuronpedia

    INDEX
    Explanations

    instances of interactions or communications between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vieles
    -0.63
    Anything
    -0.60
    anything
    -0.60
     Anything
    -0.59
     anything
    -0.59
     ANYTHING
    -0.54
     tudo
    -0.53
     debout
    -0.52
     Protestantism
    -0.51
     Communism
    -0.51
    POSITIVE LOGITS
     colleagues
    0.90
     friends
    0.85
     authorities
    0.83
    GOTREF
    0.81
     officials
    0.80
     representatives
    0.79
     stakeholders
    0.78
    帖最后由
    0.77
    pective
    0.76
     customers
    0.76
    Act Density 0.320%

    No Known Activations