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

    Neuronpedia

    INDEX
    Explanations

    actions and interactions that involve emotional or social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    as
    -0.07
    aser
    -0.06
    nom
    -0.06
    no
    -0.06
    pro
    -0.05
    _MARKER
    -0.05
    esh
    -0.05
    em
    -0.05
    ither
    -0.05
    aling
    -0.05
    POSITIVE LOGITS
    PostalCodes
    0.09
    áÄį
    0.09
    éĤ£ä¸ª
    0.08
    ´Ī
    0.08
    اÙĦت
    0.08
    ügen
    0.08
    (KP
    0.08
     sợ
    0.08
    _Lean
    0.08
    該
    0.08
    Act Density 0.035%

    No Known Activations