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

    Neuronpedia

    INDEX
    Explanations

    concepts related to trust and betrayal in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.47
     يتيمه
    -0.47
    Insee
    -0.47
     Chwiliwch
    -0.46
     quantization
    -0.42
     hornblende
    -0.40
    PRWEB
    -0.38
    ✨:
    -0.38
    IBOutlet
    -0.37
    ніципалі
    -0.37
    POSITIVE LOGITS
     trust
    3.69
    trust
    3.23
    Trust
    3.13
     Trust
    3.13
     TRUST
    3.02
     trusts
    2.94
     trusting
    2.81
     trusted
    2.77
    TRUST
    2.73
     Trusts
    2.38
    Act Density 0.634%

    No Known Activations