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

    Neuronpedia

    INDEX
    Explanations

    themes related to trust, collaboration, and mutual agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erli
    -0.18
     BaseType
    -0.15
    atk
    -0.14
    asu
    -0.14
    uem
    -0.14
    ê»
    -0.14
    oltip
    -0.14
     é«
    -0.13
    jak
    -0.13
    ahun
    -0.13
    POSITIVE LOGITS
     mutual
    0.64
     mutually
    0.52
     Mutual
    0.52
    mut
    0.40
     exchange
    0.36
     parties
    0.36
     both
    0.35
    åıĮ
    0.34
    Mut
    0.34
    both
    0.34
    Act Density 0.304%

    No Known Activations