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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mutual support and interconnectedness among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Παραπομπές
    -0.57
     Sanz
    -0.56
     Stras
    -0.55
     Thad
    -0.54
     ksi
    -0.54
    reif
    -0.53
     épis
    -0.53
     tritium
    -0.53
     Saras
    -0.53
    Vielen
    -0.52
    POSITIVE LOGITS
    feinander
    0.95
     einander
    0.90
    お互
    0.88
     nhau
    0.87
     elkaar
    0.82
     mutu
    0.81
     eachother
    0.80
    selves
    0.80
    usermodel
    0.75
     mutually
    0.75
    Act Density 0.070%

    No Known Activations