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

    Neuronpedia

    INDEX
    Explanations

    instances of trust and the dynamics involved in trusting relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilan
    -0.17
    aggi
    -0.16
    egr
    -0.15
    ntax
    -0.15
    topics
    -0.15
    ãİ¡
    -0.14
     Awareness
    -0.14
    serter
    -0.14
    ogui
    -0.14
    enser
    -0.14
    POSITIVE LOGITS
     implicitly
    0.28
     judgment
    0.23
    implicitly
    0.23
     abilities
    0.21
     judgement
    0.21
     instincts
    0.20
     implicit
    0.20
     reliability
    0.20
     authority
    0.19
     enough
    0.18
    Act Density 0.118%

    No Known Activations