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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and communication in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лем
    -0.14
    ynet
    -0.13
    ooter
    -0.13
    лим
    -0.13
    igos
    -0.13
    _combo
    -0.13
    933
    -0.13
     Companion
    -0.13
    ALE
    -0.12
     Cass
    -0.12
    POSITIVE LOGITS
     communication
    0.77
     Communication
    0.66
    communication
    0.65
    Communication
    0.63
     communications
    0.62
     comunic
    0.52
     communicate
    0.52
     Communications
    0.52
    communications
    0.51
    Communic
    0.50
    Act Density 0.154%

    No Known Activations