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

    Neuronpedia

    INDEX
    Explanations

    concepts related to belonging and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ãło
    -0.16
    .named
    -0.15
     cms
    -0.14
    .Interop
    -0.14
    raf
    -0.14
    ازÙĩ
    -0.14
     Barrier
    -0.14
     Bubble
    -0.14
    -len
    -0.14
     bubb
    -0.13
    POSITIVE LOGITS
     pert
    0.75
     Pert
    0.65
    pert
    0.61
     Bel
    0.57
    bel
    0.54
    Bel
    0.50
     appart
    0.48
     BEL
    0.47
     gehört
    0.47
     належ
    0.46
    Act Density 0.144%

    No Known Activations