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

    Neuronpedia

    INDEX
    Explanations

    descriptors of friendly and courteous interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aufs
    -0.57
     publicidad
    -0.54
    sohn
    -0.54
     cometh
    -0.54
     pubblicità
    -0.52
     McKe
    -0.52
     paraître
    -0.51
     nokt
    -0.51
     imprend
    -0.51
     hemato
    -0.50
    POSITIVE LOGITS
     friendly
    2.82
     Friendly
    2.61
    friendly
    2.54
    Friendly
    2.52
     friendliness
    1.72
     unfriendly
    1.68
     freundlichen
    1.34
     vriende
    1.34
    友好
    1.28
     freund
    1.26
    Act Density 0.040%

    No Known Activations