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

    Neuronpedia

    INDEX
    Explanations

    references to community and inter-community interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inen
    -0.77
    pread
    -0.71
    iasis
    -0.71
    argon
    -0.70
    irection
    -0.70
    sis
    -0.69
    inx
    -0.68
    nit
    -0.68
    glers
    -0.66
    Accessory
    -0.65
    POSITIVE LOGITS
     councils
    0.93
     cohesion
    0.93
    folk
    0.89
     outreach
    0.87
     elders
    0.81
     rallied
    0.80
     communities
    0.75
     council
    0.73
     colleges
    0.73
     halls
    0.72
    Act Density 0.028%

    No Known Activations