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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to personal relationships and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rophe
    -0.15
    è§
    -0.15
     Rig
    -0.15
    praak
    -0.14
    dag
    -0.14
    ниÑĤ
    -0.14
    tol
    -0.14
    tid
    -0.13
    utoff
    -0.13
    ensa
    -0.13
    POSITIVE LOGITS
     soll
    0.19
    lassen
    0.19
     kann
    0.18
    kö
    0.16
     mus
    0.15
     muss
    0.15
     mo
    0.15
    æķ¬
    0.15
     resp
    0.15
    ability
    0.15
    Act Density 0.011%

    No Known Activations