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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal identities and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     isnt
    -0.46
     /*#__
    -0.45
    Obrázky
    -0.43
    клопе
    -0.41
     arent
    -0.41
    writeFieldEnd
    -0.39
     WaitForSeconds
    -0.39
     однако
    -0.38
     whilst
    -0.38
     wasnt
    -0.37
    POSITIVE LOGITS
     dare
    0.60
     accidentally
    0.56
     specially
    0.54
     heard
    0.52
     dares
    0.52
     always
    0.51
     suddenly
    0.50
     dared
    0.50
    GEBURTSDATUM
    0.49
     usually
    0.48
    Act Density 0.052%

    No Known Activations